Deep learning (DL) models are increasingly deployed in safety-critical applications such as face recognition, autonomous driving, and medical diagnosis. Despite their impressive accuracy, they remain vulnerable to adversarial examples - subtle perturbations that can cause incorrect predictions, i.e., the robustness issues. While adversarial training improves robustness against known attacks, it often fails to generalize to unseen or stronger threats, revealing a critical gap in robustness generalization. In this work, we propose a dual-model fuzzing framework to enhance generalized robustness in DL models. Central to our method is a lightweight metric, the Lagrangian Information Bottleneck (LIB), which guides entropy-based mutation toward semantically meaningful and high-risk regions of the input space. The executor uses a resistant model and a more error-prone vulnerable model; their prediction consistency forms the basis of agreement mining, a label-free oracle for isolating decision-boundary samples. To ensure fuzzing effectiveness, we further introduce a task-driven seed selection strategy (e.g., SSIM for vision) that filters out low-quality inputs. We implement a prototype, TWINFUZZ, and evaluate it on six benchmark datasets and nine DL models. Compared with state-of-the-art testing approaches, TWINFUZZ achieves superior improvements in both training-specific and generalized robustness.

Abstract The rapid growth of the low-altitude economy, including unmanned aerial vehicles (UAVs) and urban air mobility (UAM), is reshaping industries from transportation to emergency response. Powered by advances in fifth-generation (5G) and 5G-advanced (5.5G) connectivity, artificial intelligence (AI), and new energy systems, these platforms are becoming increasingly autonomous and capable. However, their growing software complexity introduces critical cybersecurity risks. Vulnerabilities in communication protocols, onboard firmware, and AI systems can be exploited to hijack UAVs, disrupt operations, or leak sensitive data. While research has addressed isolated aspects, a unified security perspective is still lacking. This work presents a systematic review of software-level security challenges and defenses in low-altitude UAV/UAM systems. We first categorize major attack surfaces across communication, firmware, and AI layers. Furthermore, we survey defense mechanisms suited to real-time, resource-constrained aerial platforms. Finally, we propose future directions, including quantum-resistant communication protocols, hardware-software cosecurity, and edge-AI-driven architectures. Our work aims to inform researchers, practitioners, and regulators in developing integrated, resilient security strategies for the evolving low-altitude ecosystem.

The rapid development of Internet technology has made social networks central platforms for information dissemination and acquisition. As key participants, users exhibit increasingly complex connection patterns, reflecting the dynamic nature of online interactions. Therefore, in order to better understand and manage social networks, analyzing these connection patterns, particularly identifying the potential connections between users with similar tendencies, has become a critical research focus in social network studies. Nevertheless, the existing methods exhibit limitations in comprehensively harnessing the heterogeneous nature of social networks and usually over-rely on local network structures while neglecting global patterns. To address these problems, we propose an innovative method based on weighted random walks within heterogeneous information networks (HINs). We first employ HINs to structurally represent and systematically organize complex social network data, leveraging meta-paths to model user connection patterns at semantic levels. Then, based on the meta-paths, we develop an adaptive weighted random walk strategy to integrate global structural features with local semantic information and connect users with similar tendencies. Experimental results on both Twitter and public HIN datasets demonstrate that our method outperforms other classical methods in accurately connecting users with similar tendencies.

Artificial Intelligence (AI) technology has been widely used in malware detection and has significantly improved defense against cyberattacks. Existing deep learning-based methods rely on training with large-scale data and only on predefined categories, making them inadequate for rapidly responding to novel malware attacks. Malware classification based on few-shot learning has made some progress in identifying unknown malware using limited data. However, existing methods struggle to achieve high performance because they typically focus on a single malicious feature, such as a single malware image or an API call sequence, thereby ignoring the multi-dimensional nature of malware. To deal with these challenges, we propose a multi-view few-shot learning method for malware classification. We propose a multi-view malicious feature engineering scheme, which combines domain knowledge and expert experience to analyze the malware from various perspectives. Furthermore, we propose a support-query prototype generation method based on multi-view malicious features to generate higher-quality malware prototypes, which enhances the representation of novel malware family distributions. Extensive experiments show that the proposed method outperforms existing state-of-the-art approaches. With only two samples per family, the accuracy still exceeds 90%. Our method demonstrates superior cross-dataset recognition capabilities, thereby fully illustrating its robustness and generalizability across different data distributions.

Auditing differential privacy (DP) guarantees often relies on querying trained models with specially crafted queries, such as canaries, examples differing between two neighboring datasets. However, in this work, we revisit this common approach and identify a fundamental limitation: canary-based queries may not capture the strongest privacy leakage, as the most informative queries can shift during the training process. This mismatch can result in loose lower bounds on the privacy parameter$\varepsilon$, underestimating potential risks from query-based adversaries. To address this issue, we propose two methods. First, we introduce a consistent and optimizable surrogate privacy loss function that better aligns with the true privacy loss, called Privacy-loss Maximization Method (PMM), enabling systematic discovery of stronger queries through optimization. Second, we analyze how the optimal queries evolve with model training and propose a gradient-aligned query generation algorithm, called Gradient-Guided Querying (GGQ), that rapidly identifies high-risk queries by aligning their gradients with the distribution of model parameters. Empirical evaluations across multiple tasks demonstrate that our methods consistently produce stronger privacy audit results, offering a more accurate assessment of the privacy risks associated with training algorithms.

To ensure data robustness, users typically create replicas of critical data and store them on multiple servers. However, due to server failures or malicious attacks, these replicas may face the risk of loss or tampering. Therefore, periodic auditing of data replicas is necessary to ensure their integrity. Existing solutions perform periodic auditing with generating metadata for each replica individually. However, generating auditing metadata for every replica incurs significant computational overhead, and storing metadata for multiple replicas also imposes a considerable storage burden. To reduce this overhead and optimize the efficiency of auditing towards multiple replicas, we propose collusion-resistant multi-replica data auditing with optimized metadata generation (CRMRDA). First, CRMRDA enhances replica generation efficiency by employing symmetric encryption and random masking. An indistinguishable challenge strategy is introduced, making the number of generated auditing metadata copies independent of the number of replicas. Second, we construct a security model for multi-replica data possession that allows server collusion and provide a formal security proof for CRMRDA. In addition, CRMRDA supports practical features such as dynamic operations and batch auditing. Finally, the efficiency of CRMRDA is evaluated in an experimental environment consisting of four servers, one third-party auditor, and one data owner. Compared to the latest multi-replica data auditing schemes, CRMRDA demonstrates lower computational overhead in replica generation, metadata generation, and periodic auditing.

Untargeted poisoning membership inference (PMI) attacks are a newly emerging privacy threat that evaluates the impact of poisoned samples on the privacy leakage risk in the model's training dataset. Existing approaches typically select target samples randomly from a candidate dataset to generate poisoned samples, which are then injected into the training dataset. While effective in amplifying privacy leakage risks, this random selection strategy overlooks the fact that each poisoned sample contributes unequally to the attack. In this paper, we first observe that randomly selected target samples may be distant from and dispersed relative to high-confidence benign samples, which restricts the effectiveness of membership inference attacks. We then show that selecting target samples with high confidence in their ground-truth class to generate poisoned samples contributes more significantly to the attack. Therefore, we propose a novel untargeted PMI attack incorporating the target sample selection and enhancement. Specifically, we train shadow models to select the highest-confidence target samples for poison generation. To further enhance the effectiveness of the attack, we introduce a noise generator that adds adversarial perturbations to the selected target samples. Experimental results demonstrate that our approach significantly improves the attack success rate (e.g.,$85.6\%$compared to the baseline of$71.9\%$). Notably, the ablation study shows that our noise generator enhances privacy leakage risks even when target samples are selected randomly, highlighting its effectiveness and broad applicability.

With the rapid growth of mobile applications, large volumes of private data are continuously generated on mobile devices and increasingly outsourced to cloud storage services. Due to the limited computational and energy resources of mobile devices, enabling efficient and secure periodic auditing of cloud stored data remains a challenging task. Existing cloud data auditing schemes, such as Provable Data Possession and Proof of Retrievability, require computation-intensive operations that are impractical for resource-constrained mobile environments. To address this challenge, we propose MIDAS, a mobile-friendly data auditing scheme that supports secure outsourcing of auditing metadata with balanced resource utilization. MIDAS adopts a two-phase auditing metadata structure, in which computation intensive operations are offloaded to edge nodes, while mobile devices only perform lightweight processing. In addition, identity information of edge nodes is embedded into the auditing metadata to support traceability and accountability. To further improve scalability, we design a resource scheduling model for Multi MU and Multi-EN scenarios and propose the proportional load balanced scheduling algorithm to achieve efficient and load balanced metadata generation. The security of MIDAS is rigorously proven by reducing it to the discrete logarithm problem in the RSA quadratic residue subgroup within the random oracle model. Experimental results in a real-world environment demonstrate that MIDAS significantly reduces computational overhead on mobile devices, maintains acceptable communication cost, and achieves superior scalability compared with existing schemes.

The rapid evolution of digital currency trading, fueled by the integration of blockchain technology, has led to both innovation and the emergence of smart Ponzi schemes. A smart Ponzi scheme is a fraudulent investment operation in smart contract that uses funds from new investors to pay returns to earlier investors. Traditional Ponzi scheme detection methods based on deep learning typically rely on fully supervised models, which require large amounts of labeled data. However, such data is often scarce, hindering effective model training. To address this challenge, we propose a novel contrastive learning framework, CASPER (Contrastive Approach for Smart Ponzi detectER with more negative samples), designed to enhance smart Ponzi scheme detection in blockchain transactions. By leveraging contrastive learning techniques, CASPER can learn more effective representations of smart contract source code using unlabeled datasets, significantly reducing both operational costs and system complexity. We evaluate CASPER on the XBlock dataset, where it outperforms the baseline by 2.3% in F1 score when trained with 100% labeled data. More impressively, with only 25% labeled data, CASPER achieves an F1 score nearly 20% higher than the baseline under identical experimental conditions. These results highlight CASPER's potential for effective and cost-efficient detection of smart Ponzi schemes, paving the way for scalable fraud detection solutions in the future.

Source code vulnerabilities represent a critical threat to software security, potentially leading to severe consequences such as data breaches and system failures. Traditional static analysis tools, while widely used, suffer from high false positive rates and struggle to adapt to the increasing complexity of modern software. Deep learning-based approaches hold promise for automated vulnerability detection, but they face challenges including limited dataset quality, inadequate feature extraction, and lack of precise vulnerability localization capabilities. To address these limitations, we propose MaliVD, a novel vulnerability detection method in source code that leverages a multi-modal attention mechanism. MaliVD not only identifies vulnerability types but also pinpoints the specific lines of code where vulnerabilities are triggered. The model extracts sequential, tree-based, and graph-based features from source code and employs specialized neural networks to learn these diverse representations. By strategically focusing on Points of Interest within the code, MaliVD effectively prioritizes potentially vulnerable code regions, enhancing both detection accuracy and localization precision. Experimental results show that when compared with eight advanced vulnerability detection models across three large datasets, MaliVD demonstrates superior vulnerability detection and localization capabilities, maintaining highF1scores and localization precision. Particularly on the ReliVul dataset, theF1score is improved by 21.82%, and the Top-5 localization accuracy is 18% higher than other methods, with lower false positives across six mainstream vulnerability types, validating MaliVD’s practical application value in real-world environments.

Reliable protocol knowledge is often difficult to obtain in industrial networks, as industrial communications come with limited documentation, vendor-specific encodings, and opaque payloads. This lack of transparency hinders message interpretation and protocol analysis. To recover this missing protocol knowledge, network-trace-based protocol reverse engineering (PRE) infers message structure, field roles, and interaction logic directly from recorded traces. This enables protocol-aware intrusion detection, process monitoring, and protocol testing and fuzzing without access to device internals. Although PRE has advanced rapidly, existing techniques are developed under diverse objectives and assumptions. As a result, it is often unclear how isolated results relate to an end-to-end reverse-engineering workflow, and how evaluation outcomes should be compared across tasks and protocols. In this article, we cast reverse engineering of industrial protocols from network traces as a task-driven pipeline and articulate a unified task decomposition spanning message type identification, protocol syntax and semantic inference, payload pattern recognition and semantic inference, and protocol state machine reconstruction. For each task, we describe key methodological themes, common evaluation practices, and practical limitations that affect robustness and deployability in industrial settings. We further discuss security, privacy, and ethical risks that accompany increasingly capable PRE, and identify promising research directions toward more systematic, dependable, and deployment-oriented PRE methodologies.

Deep learning (DL) libraries are widely used to form the basis of various AI applications in computer vision, natural language processing, and software engineering domains. Despite their popularity, DL libraries are known to have vulnerabilities, such as buffer overflows, use-after-free, and integer overflows, that can be exploited to compromise the security or effectiveness of the underlying libraries. While traditional fuzzing techniques have been used to find bugs in software, they are not well-suited for DL libraries. In general, the complexity of DL libraries and the diversity of their APIs make it challenging to test them thoroughly. To date, mainstream DL libraries like TensorFlow and PyTorch have featured over 1,000 APIs, and the number of APIs is still growing. Fuzzing all these APIs is a daunting task, especially when considering the complexity of the input data and the diversity of the API usage patterns. Recent advances in large language models (LLMs) have illustrated the high potential of LLMs in understanding and synthesizing human-like code. Despite their high potential, we find that emerging LLM-based fuzzers are less optimal for DL library API fuzzing, given their lack of in-depth knowledge on API input edge cases and inefficiency in generating test inputs. In this paper, we propose DFuzz, a LLM-driven DL library fuzzing approach. We have two key insights: (1) With high reasoning ability, LLMs can replace human experts to reason edge cases (likely error-triggering inputs) from checks in an API's code, and transfer the extracted knowledge to test other (new or rarely-tested) APIs. (2) With high generation ability, LLMs can synthesize initial test programs with high accuracy that automates API testing. DFuzz provides LLMs with a novel “white-box view” of DL library APIs, and therefore, can leverage LLMs' reasoning and generation abilities to achieve comprehensive fuzzing. Our experimental results on popular DL libraries demonstrate that DFuzz is able to cover more APIs than SOTA (LLM-based) fuzzers on TensorFlow and PyTorch, respectively. Moreover, DFuzz successfully detected 37 bugs, with 8 already fixed and 19 replicated by the developer but still under investigation.

The automation of unit test generation has become a critical task for improving the overall efficiency of software development and testing. Many existing techniques attempt to generate a sufficient number of test cases to achieve high code coverage. However, it has been shown that a high coverage does not necessarily guarantee effective bug discovery. A potential enhancement is to guide the unit test generation based on bug properties. However, this solution is challenged by the large number and diversity of bug types, making it difficult to comprehensively summarize bug properties.We observe that failures, presented as the results of bugs, manifest in a limited number of scenarios. Therefore, instead of bug properties, in this paper, we propose an innovative framework, named FailMapper, which uses failure scenarios to guide the generation of unit tests. We summarize nine failure scenarios and design the corresponding failure-triggering test strategies. This significantly improves the efficacy of generating test cases towards triggering bugs. To systematically explore possible failure scenarios, FailMapper employs the Monte Carlo Tree Search algorithm to search for the faults that may lead to a failure. Experiments demonstrate that, on 50 known bugs in the Defects4J benchmark, FailMapper can detect many more bugs than five typical unit testing approaches, including EvoSuite, Randoop, CoverUp, HITS, and SymPrompt (40 versus at most 12, out of all 50 bugs). Meanwhile, FailMapper detects 12 out of 20 bugs in the GitBug-Java and Bears-benchmark datasets. We reveal 36 potential issues from 2 Apache projects, and 14 of them have been confirmed as bugs, further demonstrating FailMapper’s effectiveness. The experimental results show that our new framework can significantly enhance the overall efficacy of unit testing.

The Internet of Things (IoT) is widely used in various sectors but is often prone to vulnerabilities. With the proprietary nature of IoT devices, their source code and firmware are frequently unavailable for open review, rendering blackbox fuzzing a viable approach. However, the effectiveness of blackbox fuzzing is often challenging due to the lack of feedback, especially the information of code coverage. In this paper, we propose WingMuzz to provide blackbox fuzzing of IoT protocols with effective feedback. The key is to guide blackbox fuzzing by utilizing runtime information from greybox fuzzing on counterpart open-source code. This is based on our observation that IoT protocols and open-source code conform to the same specifications, indicating that inputs exploring different code regions on open-source code may also discover new coverage on IoT protocols. WingMuzz uses a two-dimensional fuzzing schedule to optimize the process of fuzzing IoT protocols. The first dimension involves scheduling open-source implementations, referred to as wingmates, so that similar ones are preferred to guide blackbox fuzzing. The second dimension utilizes coverage-guided greybox fuzzing to test open-source code. This solution can bridge the performance gap between blackbox fuzzing and greybox fuzzing on IoT protocols. We evaluate the performance of WingMuzz across eight IoT protocols and compare it with six widely-used blackbox fuzzers. On average, WingMuzz can discover 42.1%, 26.92%, 25.01%, 34.95%, 23.56% and 11.63% more edges than Boofuzz, Spike, Peach, Snipuzz, Pulsar and ChatAFL, respectively. Additionally, WingMuzz exposes 10 bugs in IoT protocols while other fuzzers expose no more than 3 bugs. It also exposes 2 new protocol vulnerabilities in IoT devices while other fuzzers cannot identify any.

With the rapid adoption of LLM-based code assistants to enhance programming experiences, concerns over extraction attacks targeting private training data have intensified. These attacks specifically aim to extract Personal Information (PI) embedded within the training data of code generation models (CodeLLMs). Existing methods, using either manual or semi-automated techniques, have successfully extracted sensitive data from these CodeLLMs. However, the limited amount of data currently retrieved by extraction attacks risks significantly underestimating the true extent of training data leakage. In this paper, we propose an automatic PI data extraction attack framework against LLM-based code assistants, named Codebreaker. This framework is built on two core components: (i) the introduction of semantic entropy, which evaluates the likelihood of a prompt triggering the model to respond with training data; and (ii) an automatic dynamic mutation mechanism that seamlessly integrates with Codebreaker, reinforcing the iterative process across the framework and promoting greater interconnection between different PI elements within a single response. This boosts reasoning diversity, model memorization, and finally attack performance. Using six series of open-source CodeLLMs (i.e., CodeParrot, StarCoder2, Code Llama, CodeGemma, DeepSeek-Coder, DeepSeek-V3) and two commercial code assistants (i.e., CodeFuse and GPT), we demonstrate the effectiveness of our proposed framework: (i) Codebreaker outperforms all current state-of-the-art extraction attacks by 6.22% ~ 44.9% (averaging 21.79%); (ii) when PI within a single response originates from the same GitHub repository, our framework - considering multiple interconnections in the response - exceeds others by 3.88% ~ 32.37% (averaging 15.31%). Furthermore, we discuss potential defenses, highlighting the urgent need for stronger measures to prevent PI leakage at the base model level.

Cross-chain bridges, one of the foundational infrastructures of blockchain, provide the infrastructure and solutions for inter-operability, asset liquidity, data transfer, decentralized finance, and cross-chain governance between blockchain networks. However, because cross-chain bridges often have to handle communication and asset transfers between multiple blockchains, they involve complex protocols and technologies. This complexity increases the likelihood of vulnerabilities and potential attacks. In order to ensure the security and reliability of cross-chain bridges, this article launches a thorough investigation of existing cross-chain bridge projects, clarifying bridging mechanisms, bridge types, and security features. The following part goes into the subject of security and sheds light on the considerable challenges faced by cross-chain bridges. It conducts a thorough analysis of security flaws, covering problems like smart contract vulnerabilities, centralization risks, liquidity issues, and oracle manipulations. Furthermore, this study promotes a compendium of security solutions and best practises, pointing the way toward a cross-chain bridge scenario that is more secure.

AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of society, offering significant implications for efficiency, security and resilience. While adopting decentralized AI approaches (such as federated learning technology) in ACIs is plausible, private and sensitive data are still susceptible to data reconstruction attacks through gradient optimization. In this work, we propose Compressed Differentially Private Aggregation (CDPA), a leakage-resilient, communication-efficient, and carbon-neutral approach for ACI networks. Specifically, CDPA has introduced a novel random bit-flipping mechanism as its primary innovation. This mechanism first converts gradients into a specific binary representation and then selectively flips masked bits with a certain probability. The proposed bit-flipping introduces a larger variance to the noise while providing differentially private protection and commendable efforts in energy savings while applying vector quantization techniques within the context of federated learning. The experimental evaluation indicates that CDPA can reduce communication cost by half while preserving model utility. Moreover, we demonstrate that CDPA can effectively defend against state-of-the-art data reconstruction attacks in both computer vision and natural language processing tasks. We highlight existing benchmarks that generate 2.6x to over 100x more carbon emissions than CDPA. We hope that the CDPA developed in this paper can inform the federated AI-enabled critical infrastructure of a more balanced trade-off between utility and privacy, resilience protection, as well as a better carbon offset with less communication overhead.

Fuzzing is a critical technique for uncovering vulnerabilities in software libraries. However, current approaches often struggle with cross-language compatibility and integration with diverse fuzzing tools. We proposeEXo-Muta, a novel universal library fuzzing framework based on exogenous mutation. We use the term ‘exogenous’ to describe this new mutation process because it operates externally to the fuzzer's core engine, executing within the fuzz driver as an independent component, unlike traditional endogenous mutations tightly integrated within the fuzzer itself. By decoupling the mutation process from specific fuzzers,EXo-Mutaachieves unprecedented adaptability across diverse programming languages and fuzzing tools. It leverages static analysis to extract structured data representations and applies language-independent mutation operators at the code level. This design enables seamless integration with various existing fuzzers, enhancing their performance regardless of the target language. We further utilize large language models (LLM) for efficient cross-language data conversion. In experiments, we evaluatedEXo-Mutaon 20 real-world libraries across C++, Python, Java, and JavaScript, integrating it with multiple stateof- the-art fuzzers, such as AFL++ and libFuzzer, and languagespecific tools, such as Atheris and Jazzer. Results show significant improvements in code coverage across different fuzzers and languages, with up to 58% more edges discovered in C++ projects when integrated with libFuzzer, and consistent outperformance in other scenarios (27% on Python, 9% on Java, 6% on JavaScript).EXo-Mutarepresents a significant advancement in fuzzing technology, offering a universal, language-agnostic approach that substantially improves code coverage across diverse programming languages and fuzzing tools, thereby expanding the reach and effectiveness of library API testing.

As one of the most successful techniques in hunting software bugs, Coverage-guided Greybox Fuzzing (CGF) intends to move fuzzing campaigns towards executions that can trigger bugs. This process can be divided into two steps, including reaching suspicious code regions and exploring their execution states. Many CGFs propose approaches to efficiently reach suspicious code regions and individual execution states, but fail to explore complex execution states. The challenge is how to explore execution states so that fuzzing can detect multiple types of bugs, while maintaining the code coverage. To address this challenge, we proposeBazzAFLto investigate code coverage and multiple types of bugs. The crux ofBazzAFLis to maintain a bunch of seed groups, where each seed saves the best performance on one objective. With the seed group,BazzAFLprioritizes code regions that most likely contain bugs based on multi-objective optimization and adaptively divides energy among the seeds in a group based on Shannon's entropy. Meanwhile, during mutation,BazzAFLtends to mutating the bytes that can change the execution states. With these solutions,BazzAFLgradually moves fuzzing campaigns towards locations and execution states of bugs. Experimental results show thatBazzAFLidentifies at least 62 more bugs on 24 programs compared with other fuzzers.

Critical infrastructures are increasingly integrating artificial intelligence (AI) technologies, including large language models (LLMs), into essential systems and services that are vital to societal functioning. Fine-tuning LLMs for specific domain tasks are crucial for their effective deployment in these contexts, but this process must carefully address both privacy and security concerns. Without proper safeguards, such integration can introduce additional risks, such as data leakage during training and diminished model trustworthiness due to the need for model compression to operate within limited bandwidth and computational capacity constraints. In this paper, we proposeHardening LLM Fine-tuning framework(HARDLLM), which addresses these challenges through two key components: (i) we develop a differentially private data selection method that ensures privacy protection by training the model exclusively on sampled and synthesized public data, thereby preventing any direct use of private data and enhancing leakage resilience throughout the training process, and (ii) we introduce a trustworthiness-aware model quantization approach to improve LLMs performance, such as reducing toxicity, enhancing adversarial robustness, and mitigating stereotypes, while maintaining negligible impact on model utility. Experimental results show that, the proposed algorithm ensures differential privacy when privacy budget is set at ϵ = 0.5, with only a 1% drop in accuracy, while other state-of-the-art methods experience an accuracy drop of at least 20% under the same privacy budget. Additionally, our quantization approach improves the trustworthiness of fine-tuned LLMs by an average of 3-4%, with only a negligible utility loss (approximately 1%) at a 50% compression rate.

Model inversion (MI) attacks, for which effective defense strategies are still lacking, pose significant risks to privacy by reconstructing private training data through access to well-trained classifiers. Addressing this concern, this study introduces TrapNet, designed to defend against advanced MI attacks while maintaining good model utility. TrapNet intentionally injects trapdoors into the classification manifold of the protected target model. In this way, TrapNet can effectively mislead MI attack optimization. Specifically, TrapNet leverages a conditional GAN (cGAN) trained on the private dataset to generate diverse and realistic trapdoor samples. In addition, we propose a graph-matching self-obfuscation strategy and an entropy regularization technique to optimize trapdoor injection while preserving model utility. Compared to the existing defense, TrapNet can provide universal protection to all target classes without access to any auxiliary public data. Extensive experiments on CelebA, VGG-Face, and VGG-Face2 datasets demonstrate TrapNet’s superior performance over existing defenses, including the most advanced NetGuard and BiDO, against state-of-the-art model inversion attacks, i.e., PLG-MI, LOMMA, and Plug&Play.

As the Industrial Internet of Things (IIoT) continues to expand, the need for effective device identification becomes critical for securing industrial environments. Network traffic fingerprinting has emerged as an important technique for IIoT device identification, leveraging the unique communication patterns embedded in network traffic. Despite significant efforts in this area, a comprehensive overview of the relevant research is still missing. To address the lack of comprehensive research, this paper, for the first time, identifies critical knowledge gaps constraining IIoT device identification through network traffic analysis: obscure fingerprint feature space, limited generalizability to unknowns, and scarce data sources. Focusing on these gaps, existing methods are analyzed and summarized in detail across network traffic fingerprinting, IIoT device identification, and public IIoT datasets. Specifically, network traffic fingerprinting methods are categorized into three levels: Packet-level, flow-level, and business-level, and relevant methods are examined in terms of data formats, segmentation units, and extraction or generation techniques. In the context of IIoT device identification, tasks such as device type, model, and instance recognition, as well as abnormal device detection, are extensively investigated using rule-based, traditional machine learning- based, and deep learning-based approaches, with a focus on device fingerprints and application scenarios. Furthermore, main public datasets from the IoT, ICS, and IIoT scenarios are highlighted to support the development of fingerprinting and identification methods. Finally, several future research directions are proposed to guide new advancements in this area.

The Internet of Robotic Things (IoRT) has experienced rapid growth and garnered increased attention in recent years. Applications (Apps) play a crucial role in IoRT, as they provide users with an intuitive interface to access and operate services. However, as user demands increase, Apps become more complex, leading to longer operation sequences and more vulnerabilities. The existing testing methods for Apps can be categorized into random, reinforcement learning, and AI-based approaches. AI-based methods offer a solution to the low coverage efficiency of random-based methods and the weak guidance of reinforcement learning-based methods. However, current AI-based methods have difficulty in capturing long-term dependencies, resulting in low coverage and less detected crashes when testing Apps with long operation sequences. To address the limitation, we propose InforTest, a novel AI-based method based on the Informer prediction model and the component tree structure. InforTest leverages Informer, which excels at extracting long-term dependencies from operation sequences, to generate human-like moves for testing Apps. To improve the efficiency of training and prediction, InforTest uses the component tree, a concise structure to represent primary data sources, i.e., screenshots. After training InforTest on the Rico dataset, our experiments with Apps in the IoRT scenario demonstrated its superiority over existing methodologies such as Monkey, Humanoid, MUBot, and Ape. Notably, InforTest achieved significant enhancements in coverage rates (increases of 67%, 34%, 19%, and 27%, respectively) and in crash detection capabilities (improvements of 175%, 81%, 71%, and 139%, respectively).

In low-light environments, human vision is severely limited by weak light sources, leading to significantly reduced visual capabilities. Similarly, in machine vision, low-light recognition tasks such as nighttime autonomous driving and surveillance tasks involving the detection of small faces in low-light conditions are more challenging than tasks in normal lighting. Current low-light face detection models lack adaptability to different low-light conditions, and the accuracy of face detection remains unsatisfactory. In this paper, we propose a novel face detection framework DSLL-Face, specifically designed to tackle the challenges of face detection in low-light environments. Our proposed DarkHead, featuring a specialized branch designed to predict the distribution of bounding boxes, thereby substantially enhances the supervision of bounding box localization. This innovative approach effectively resolves the issue of blurry bounding boxes and significantly increases the accuracy of predicted positions. We employ a novel loss function tailored for detecting small faces, enhancing the sensitivity and effectively addressing the blurriness issues in small face detection. Furthermore, we leverage the Channel Grouping and Partial Convolution block (CGP) to enhance multi-scale expression capabilities. We develop the EMNet-pro model with the aim of further enhancing images to improve their adaptability under various low-light conditions. Extensive experiments demonstrate that our model exhibits outstanding capability in low-light face detection on the DARK FACE dataset and achieves significantly better performance compared to existing state-of-the-art frameworks.

There are many instances of helical mechanisms that are used to efficiently grasp different objects with various shapes and sizes in nature. Inspired by the helical grasping in the nature, we proposed a helical bistable soft gripper with high load capacity and energy saving. An off-the-shelf bistable steel shell (BSS) as the stiff element was inserted into a 3D printing soft helical exoskeleton to achieve coiling around and holding the objects without energy consumption. Two air pouches were designed as the actuator to control the transition between the two stable states. To facilitate gripper design, a simplified model of the gripper was conducted, and the geometric parameters of the gripper are listed in a table for reference. The transition pressures between the two stable states were experimentally characterized. Moreover, we conduct experiments to demonstrate the capability of the gripper in two working modes. The gripper exhibits coiling diameters ranging between 40 mm and 60 mm and is successfully attached to various slender objects of different geometries with a maximum holding force of 92.67 N (up to 135.1 times of its mass) in hanging mode. Finally, the gripper was integrated into a robot arm and successfully grasped different objects, and the maximum grasping weight is 221.6 g in the grasping mode.

The transferability of adversarial examples is pivotal in black-box attacks on deep learning models. The existing transfer-based attacks typically rely on a single data augmentation technique, which hampers the diversity of generated adversarial examples. Additionally, applying a single adversarial noise generation path may impose limitations on the perturbation strength of the generated noise, thereby compromising the transferability of these examples. To address these issues, we propose a framework called Joint Training and Dual Feature Mixiup (JFM), which comprises the dual feature mixup module and joint training module. The dual feature mixup module performs feature mixing between benign and augmented images, enabling the comprehensive extraction of benign example features and enhancing the diversity of adversarial examples. Furthermore, the joint training module designs a dual-path prediction loss function that incorporates both the loss between mixed feature examples and benign examples, as well as the loss between augmented examples and benign examples, thereby enhancing the transferability of the generated examples. Empirical evaluation of the ImageNet-compatible dataset demonstrates that our JFM method exhibits superior attack capability and significantly outperforms state-of-the-art methods.

In recent years, the utilization of Ethereum has significantly increased, positioning it as a favored platform among criminal entities. A recently proposed blacklisting method offers a compelling approach; however, its implementation faces numerous challenges. For instance, criminals may circumvent the blacklisting mechanism by creating new addresses and there are several ambiguities in their explanation. This paper explores the increasing use of Ethereum for criminal activities, focusing on the challenges of enforcing blacklisting to curb illegal transactions. We analyse blacklisting within cryptocurrency networks, particularly Ethereum, and develop features to detect illegal patterns. The study identifies unique issues in transaction networks that require specialised solutions beyond general cryptocurrency techniques. We propose a detection model based on these features and validate its effectiveness using real Ethereum datasets. The paper also reviews regulatory guidelines, highlighting ambiguities in their interpretation. Experiments on real-world data underscore the need to integrate technical methods and consider Shapley-value-based frameworks in designing effective solutions. The novelty of the method lies in its development of a feature-based detection model, leveraging Shapley-value frameworks to enhance explanation, address Ethereum’s unique challenges, and empirically validate its effectiveness using real Ethereum data, offering a more robust solution than traditional blacklisting approaches.

Since the outbreak of the coronavirus 2019 (COVID-19) pandemic, telehealth services are regarded as a good approach to keep health workers and patients safe while simultaneously managing available resources.In this paper, we discuss the impact that COVID-19 has on telehealth services and on telehealth users' opinion of the service.We collected 245 Android telehealth apps, 144 iOS telehealth apps and 86 telehealth websites, and performed a systematic analysis on this dataset.In this analysis, we conducted a comparison analysis and relevant content analysis of the telehealth apps as well as their security risks.Apart from the mobile platforms, we also inspected the telehealth websites' features, particularly those related to the use of metaverse to improve current telehealth solutions.To further understand people's attitude towards telehealth services, we invited users to participate in a user study aimed at revealing what impact COVID-19 has on users' willingness to adopt telehealth services and revealing the gap between the telehealth service and its users.Our result shows that 27.1% new iOS apps and 27.4% new Android apps were released after the COVID-19 announcement, and a surge of updates were noted within 4 weeks after the COVID-19 announcement.We further found that COVID-19 is frequently mentioned in telehealth app reviews in the second and third quarter of 2020, and the most mentioned aspects related to COVID-19 include family, test result and vaccine.According to our user study, COVID-19 has a significant impact on the selection of telehealth services, especially for female participants, people aged 46-55, and students.The investigation also finds out that the use of metaverse will significantly improves the effectiveness of traditional telehealth solutions.

A smart contract is a computerised transaction agreement that carries out predefined terms without human involvement or third-party intermediaries. It serves as a trust intermediary in several industries, including finance, insurance, and supply chain management, in the blockchain 2.0 era. With the increasing interest in smart contracts, security has become a serious problem. Examining typical vulnerability types and vulnerability detection methodologies is of special importance. In this research, a comprehensive evaluation of common smart contract security vulnerabilities is conducted, and a three-tier threat model is then provided to classify the vulnerabilities. In addition, we examine fourteen existing smart contract analysis tools for finding vulnerabilities and classify them according to the main technique they apply. This article is designed to serve as a reference for people who wish to analyse deployed code and enhance existing detection techniques. At the conclusion, open issues and future research paths regarding smart contract vulnerability detection are presented.

Inferring the home locations of online social network (OSN) users from their corresponding account data is an important process for many applications, such as personal privacy protection and business advertising applications. The existing methods typically use a supervised learning method to infer a user's home location according to a single or partial aspect of their OSN information. However, the home location of a user may be represented in a biased way if only a single or partial aspect of the information is used, and the performances of the supervised learning-based methods are also very sensitive to the quality of the training set utilized. To address these problems, this article presents a novel unsupervised method for inferring the home locations of the OSN users. The method first builds a heterogeneous network model to comprehensively represent the complex location information in the OSN data and then recursively infers users’ home locations by fusing the direct and indirect location information of the users. Experiments that compared our method with five existing typical Twitter user home location inference methods on a Twitter dataset demonstrate that the proposed method can significantly improve the accuracy and reliability of user home location inference.

AI-powered programming language generation (PLG) models have gained increasing attention due to their ability to generate source code of programs in a few seconds with a plain program description. Despite their remarkable performance, many concerns are raised over the potential risks of their development and deployment, such as legal issues of copyright infringement induced by training usage of licensed code, and malicious consequences due to the unregulated use of these models. In this paper, we present the first-of-its-kind study to systematically investigate the accountability of PLG models from the perspectives of both model development and deployment. In particular, we develop a holistic framework not only to audit the training data usage of PLG models, but also to identify neural code generated by PLG models as well as determine its attribution to a source model. To this end, we propose using membership inference to audit whether a code snippet used is in the PLG model's training data. In addition, we propose a learning-based method to distinguish between human-written code and neural code. In neural code attribution, through both empirical and theoretical analysis, we show that it is impossible to reliably attribute the generation of one code snippet to one model. We then propose two feasible alternative methods: one is to attribute one neural code snippet to one of the candidate PLG models, and the other is to verify whether a set of neural code snippets can be attributed to a given PLG model. The proposed framework thoroughly examines the accountability of PLG models which are verified by extensive experiments. The implementations of our proposed framework are also encapsulated into a new artifact, named CODEFORENSIC, to foster further research.

The privacy of social media users is a major concern when the users share their content to the public. Sensitive information such as the location of the users can be inferred from relevant content without arising the awareness of the users. With blooming services provided by social media platforms, the users have more freedom to share information via diverse data formats. The multi-modality of the shared information may, in return, worsen the private information leakage caused by inference attacks. In this paper, we first examine the problem of location inference on multi-modal data comprised of textual information and visual content. It is observed that the visual content, such as photos shared by social media users, can significantly boost the success rate of location inference. To thwart adversaries who are driven by visual-related data, we propose a defence that mitigates the threat of location privacy breach under an imperceptible utility loss. Our defence, namely LocGuard, perturbs the photos in a one-off manner before sharing them. The perturbations, along with a simple but effective bipartite perturbation strategy, ensure that LocGuard is resistant to adaptive adversaries who can perform adversarial training based on the perturbed photos. Moreover, LocGuard remains effective against open-set adversaries whose data categories in the training dataset are hidden from the defender. In the evaluation, we conduct extensive experiments based on real-world datasets and compare our work with previous methods. The results show that LocGuard significantly outperforms the existing defences. In particular, LocGuard not only achieves better privacy protection and utility preservation for image sharing, but also can effectively defend against adversarial-training-capable attackers.

It is important to understand the evolution of Android malware as this facilitates the development of defence techniques by proactively capturing malware features. So far, researchers mainly rely on dendrogram or family-tree analysis for malware's evolutionary development. However, our research finds that these techniques cannot support comprehensive malware evolution modelling, which provides a detailed explanation for why Android malware samples evolve in specific ways. This shortcoming is mainly caused by the coarse-grained clustering and analysis of malware samples. For example, because these works do not divide malware samples of a family into variant sets and explore the evolution principles among those sets, they usually fail to capture new variants that have been empowered by the feature ‘drifting’ in evolution. To address this problem, we propose a fine-grained and in-depth analysis of Android malware. Our experimental work systematically reveals the phylogenetic relationships among the variant sets for a deeper malware evolution analysis. We introduce five metrics: silhouette coefficient, creation date, variant labels, the presentativeness of the variant set formula, and the correctness of the linked edges to evaluate the correctness of our analysis. The results show that our variant clustering achieved a high silhouette value at a small sample distance (0.3), a small standard deviation (three months and 16 days) date based on when the malware samples are lastly modified, a high label consistency (91.4%), a high representativeness (93.1%) of the variant set formula. All the linked variant sets are connected based on our PhyloNet construction rules. We further analyse the coding details of Android malware for each variant set and summarise models of their evolutionary development. In this work, we successfully expose two major models of malware evolution:active evolutionandpassive evolution. We also disclose four technical explanations on the incentives of the two evolution models (two for each model respectively). These findings are valuable for proactive defence against newly emerged malware samples.

Google suggests using only the APIs documented in Android SDK. However, many app developers still choose Java Native Interface (JNI) to access system libraries because of the flexibility and freedom that non-SDK methods provide in implementing complex functions. However, using JNI may have unexpected consequences, including low-level bug-driven crashes. The bugs in system libraries can propagate to Android apps, and further cost much time and energy for developers to debug them. We develop a fuzzing tool, called JDYNUZZ, that exposes the bugs in system JNI to mitigate the aftermath of direct invocation of JNI. To fuzz a system library, one needs to not only prepare appropriate inputs, but also deal with the challenge of maintaining a correct sequence of API calls, both syntactically and semantically. To solve the challenge, the crux of JDYNUZZ is the dynamic refinement of a data dependency graph, which gradually resolves the problem of syntactic and semantic incorrectness when constructing API sequences. JDYNUZZ achieves the dynamic refinement based on the feature of Java reflection, which enables us to dynamically modify API sequences and test different code regions. We evaluate JDYNUZZ on the most recent version of Android Open Source Project (AOSP),i.e., version android-12.0.0 r31. In our experiments, JDYNUZZ discovers 34 new bugs in system JNI libraries, all confirmed by Google.

Applying artificial intelligence (AI) to data from Industrial Internet of Things (IIoT) devices is a novel direction in geological studies. However, privacy and security concerns hinder the sharing of data, thus affecting the performance of current AI-based approaches. In this article, we propose a novel data management style to address the privacy and security issues in joint hydrocarbon explorations. Federated learning can facilitate the analysis of multiple datasets without the need to share them, protecting private information of different companies in a virtual joint venture. We use the inference of petroleum reservoirs in karst stratigraphy as a case study. A federated learning-based enterprise data management framework is proposed to virtually integrate the information from different organizations. Our key contributions are summarized as follows. 1) A method for karst identification and inference is proposed, which uses neural networks to recognize the size of petroleum reservoirs in different karst areas. 2) A federated learning algorithm is applied to virtually aggregate data samples from different companies. 3) The performance of the new privacy-preserving integration model is compared with those of the individual/local deep learning models. Our results show that the proposed approach can substantially improve the accuracy of petroleum reservoir explorations.

Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number of queries to succeed, resulting in high computational overhead in the process of attack. On the other hand, attacks with restricted perturbations are ineffective against defenses such as denoising or adversarial training. In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system. StyleFool first utilizes color theme proximity to select the best style image, which helps avoid unnatural details in the stylized videos. Meanwhile, the target class confidence is additionally considered in targeted attacks to influence the output distribution of the classifier by moving the stylized video closer to or even across the decision boundary. A gradient-free method is then employed to further optimize the adversarial perturbations. We carry out extensive experiments to evaluate StyleFool on two standard datasets, UCF-101 and HMDB-51. The experimental results demonstrate that StyleFool outperforms the state-of-the-art adversarial attacks in terms of both the number of queries and the robustness against existing defenses. Moreover, 50% of the stylized videos in untargeted attacks do not need any query since they can already fool the video classification model. Furthermore, we evaluate the indistinguishability through a user study to show that the adversarial samples of StyleFool look imperceptible to human eyes, despite unrestricted perturbations.

Businesses face a range of cyber risks, both external threats and internal vulnerabilities that continue to evolve over time. As cyber attacks continue to increase in complexity and sophistication, more organisations will experience them. For this reason, it is important that organisations seek timely consultancy from cyber professionals so that they can respond to and recover from cyber attacks as quickly as possible. However, huge surges in cyber attacks have long left cyber professionals short of what is required to cover the security needs. This problem is getting worse when an increasing number of people choose to work from home during the pandemic because this situation usually yields extra communication cost.

Summary To achieve data privacy in Internet of Things (IoT), fully homomorphic encryption (FHE) technique is used to encrypt the data while allowing others to compute on the encrypted data. However, there are many well‐known problems with FHE such as chosen‐ciphertext attack security and circuit privacy problem. In this article, we demonstrate that a famous FHE application named Brakerski/Fan–Vercauteren scheme, a circuit privacy application based on fast private set intersection, and an encoding application that encodes integer or floating point numbers based on Microsoft Simple Encryption Arithmetic Library homomorphic encryption library, are insecure against chosen ciphertext attacks due to insecurity of the underlying fully homomorphic schemes. These results show that using cryptographic primitives even with security proofs causes serious security vulnerabilities on the applications themselves. The results also give evidences that the security of adopted cryptographic primitives in IoT should be proved in appropriate formal security models as well as proof of the scheme itself.

The rapid growth of the blockchain size is a major bottleneck hindering its implementations in data-heavy applications. Current efforts improve the distributed storage ways and transactions' storage mechanisms of blockchain, however, the blockchain distribution and integrity are destroyed. Simplified Payment Verification (SPV) is closely related to blockchain storage, but the current solutions did not explore the privacy-preserving SPV. In this paper, we propose a new storage structure for blockchain transactions, called Coloring Index (CI), to reduce the blockchain's space occupation. Specifically, we devise an index building algorithm to simply calculate the indices of transactions for the sake of information concealing. By improving the Coloring Embedder for multi-sets query, we can store the indices into the Coloring Embedder to achieve the structured storage of transactions with small space occupation. Using CI, SPV query proceeds without revealing the user's address, thereby achieving secure data sharing in applications such as the intelligent vehicles' communications and distributed IoT. We prove CI's security against malicious full nodes when establishing possible connections between the address and the user. The experiments show that blockchain systems using our CI store one time more transactions than Merkle tree and half more than Bloom filter.

In the last two years, the outbreak of COVID-19 has significantly affected human life, society, and the economy worldwide. To prevent people from contracting COVID-19 and mitigate its spread, it is crucial to timely distribute complete, accurate, and up-to-date information about the pandemic to the public. In this article, we propose a spatial–temporally bursty-aware method calledSTBAfor real-time detection of COVID-19 events from Twitter.STBAhas three consecutive stages. In the first stage,STBAidentifies a set of keywords that represent COVID-19 events according to the spatiotemporally bursty characteristics of words using Ripley’s$K$function.STBAwill also filter out tweets that do not contain the keywords to reduce the interference of noise tweets on event detection. In the second stage,STBAuses online density-based spatial clustering of applications with noise clustering to aggregate tweets that describe the same event as much as possible, which provides more information for event identification. In the third stage,STBAfurther utilizes the temporal bursty characteristic of event location information in the clusters to identify real-world COVID-19 events. Each stage ofSTBAcan be regarded as a noise filter. It gradually filters out COVID-19-related events from noisy tweet streams. To evaluate the performance ofSTBA, we collected over 116 million Twitter posts from 36 consecutive days (from March 22, 2020 to April 26, 2020) and labeled 501 real events in this dataset. We comparedSTBAwith three state-of-the-art methods, EvenTweet, event detection via microblog cliques (EDMC), and GeoBurst+ in the evaluation. The experimental results suggest thatSTBAoutperforms GeoBurst+ by 13.8%, 12.7%, and 13.3% in terms of precision, recall, and$F_{1}$score.STBAachieved even more improvements compared with EvenTweet and EDMC.

Behaviour analysis is essential for the security verification of suspicious Android applications, but analysts are usually faced with a huge obstacle when conducting the app behaviour analysis. They are expected to have comprehensive knowledge of different IT fields and a strong awareness of cyber threats. However, training a new security analyst typically requires a significant amount of time and can be extremely costly. Although there are tools available to assist analysts in studying Android behaviour and security, the completion of this task still heavily relies on the experience of the analysts. To address this problem, we recognise visualisation as a promising method and conduct a series of controlled experiments to demonstrate its effectiveness in the context of Android app behaviour and security analysis. We accordingly develop a visualisation tool based on apps’ call graphs (CG) (namedVisualDroid) and conduct an experiment and a follow-up interview. Compared to existing solutions, the results suggest that the CG-based visualisation solution (VisualDroid) can lower the barriers to Android behaviour and security analysis. The user study reveals that the platform includes CG-based visualisation components leads to a statistically significant improvement in Android behaviour analysis and security awareness. More specifically, it improvesAPK Analyzer,JD-GUI,JD-GUI+FlowDroidby 71.4%, 35.7%, and 39.2% in terms of the effectiveness of behaviour analysis. Participants who useVisualDroidalso show improvements in the aspect of security awareness with an increase of 155% againstAPK Analyzer, 96% againstJD-GUI, and 59.3%JD-GUI+FlowDroid.

Location-based services (LBSs) are widely used in vehicular networks. Privacy leakage from LBS is a key issue to be solved. However, the existing schemes fail to provide differentiated protection for users’ different locations, which may lead to the leakage of location information. In this paper, we propose a personalized location privacy protection scheme based on differential privacy to protect the privacy of location-based services in vehicular networks. Firstly, we propose a normalized decision matrix to describe the efficiency and the privacy effect of navigation recommendations. We then establish a utility model integrated with users’ privacy preferences to compute the effective driving route. Secondly, for different service request locations in the driving route, we define sensitivity distance as an index to quantify their privacy requirements. The privacy budget will be added to the service request location to generate a false location. Moreover, due to the limitation of road range in the driving route, if the privacy budget value allocated is small enough, the false location generated by the Plane Laplace will be deviated. As a result, the attacker can deduce users’ real request locations. Consequently, considering the factors of trajectory leakage, attack strategy and QoS, we establish a multi-objective optimization model to optimize the false location. Based on the real data set, we conduct a series of comparison simulations to evaluate the performance of the proposed scheme. The experimental results demonstrate that our scheme can satisfy users’ personalized services needs and provide an optimal solution to privacy and QoS.

Multi-turn response selection is a key issue in retrieval-based chatbots and has attracted considerable attention in the NLP (Natural Language processing) field. So far, researchers have developed many solutions that can select appropriate responses for multi-turn conversations. However, these works are still suffering from the semantic mismatch problem when responses and context share similar words with different meanings. In this article, we propose a novel chatbot model based on Semantic Awareness Matching, called SAM. SAM can capture both similarity and semantic features in the context by a two-layer matching network. Appropriate responses are selected according to the matching probability made through the aggregation of the two feature types. In the evaluation, we pick 4 widely used datasets and compare SAM’s performance to that of 12 other models. Experiment results show that SAM achieves substantial improvements, with up to 1.5% R 10 @1 on Ubuntu Dialogue Corpus V2, 0.5% R 10 @1 on Douban Conversation Corpus, and 1.3% R 10 @1 on E-commerce Corpus.

Coverage-guided Greybox Fuzzing (CGF) is one of the most successful and widely-used techniques for bug hunting. Two major approaches are adopted to optimize CGF: (i) to reduce search space of inputs by inferring relationships between input bytes and path constraints; (ii) to formulate fuzzing processes (e.g., path transitions) and build up probability distributions to optimize power schedules, i.e., the number of inputs generated per seed. However, the former is subjective to the inference results which may include extra bytes for a path constraint, thereby limiting the efficiency of path constraints resolution, code coverage discovery, and bugs exposure; the latter formalization, concentrating on power schedules for seeds alone, is inattentive to the schedule for bytes in a seed.

The Android system manages access to sensitive APIs by permission enforcement. An application (app) must declare proper permissions before invoking specific Android APIs. However, there is no official documentation providing the complete list of permission-protected APIs and the corresponding permissions to date. Researchers have spent significant efforts extracting such API protection mapping from the Android API framework, which leverages static code analysis to determine if specific permissions are required before accessing an API. Nevertheless, none of them has attempted to analyze the protection mapping in the native library (i.e., code written in C and C++), an essential component of the Android framework that handles communication with the lower-level hardware, such as cameras and sensors. While the protection mapping can be utilized to detect various security vulnerabilities in Android apps, such as permission over-privilege, imprecise mapping will lead to false results in detecting such security vulnerabilities. To fill this gap, we thereby propose to construct the protection mapping involved in the native libraries of the Android framework to present a complete and accurate specification of Android API protection. We develop a prototype system, named NatiDroid, to facilitate the cross-language static analysis and compare its performance with two state-of-the-practice tools, termed Axplorer and Arcade. We evaluate NatiDroid on more than 11,000 Android apps, including system apps from custom Android ROMs and third-party apps from the Google Play. Our NatiDroid can identify up to 464 new API-permission mappings, in contrast to the worst-case results derived from both Axplorer and Arcade, where approximately 71% apps have at least one false positive in permission over-privilege. We have disclosed all the potential vulnerabilities detected to the stakeholders.

The security of crypto wallets is a major concern in light of the recent prevalence of thefts. Aiming at the problem that there is no complete and reliable security detection model for Android-based crypto wallets, this study provides an evaluation framework based on the standard Android application security detection and unique security assessment of crypto wallets. The framework presents an attack-based detection approach, which identifies potential wallet security issues by simulating attacks and exploiting vulnerabilities. Ten popular Android crypto wallets are evaluated and compared to validate the framework’s practicability and accuracy. The test results demonstrate that the framework can accurately reflect the performance security of wallets. Additionally, the study proposes the corresponding actions to address the identified common security threats in crypto wallets.

Summary Traditional applications have been developed for decades. Most of the security research around them have focused on the detection of memory corruption vulnerabilities, such as buffer overflow, double fetch, and integer overflow. On the contrary, logic bugs, a kind of flaws caused by unreasonable application logic, attract much less attention. Files are the most common media for programs to persist their data in the system. As the file owners, programs are responsible for protecting their files from malicious users' tampering by leveraging access control mechanisms. However, if a program configures their access control mechanisms in wrong ways and causes evil users to bypass security checks to access files, there exists a file access control vulnerability. As a branch of logic flaws, file access control vulnerabilities are less popular with researchers. Thus, to mitigate the harm of the file access control vulnerabilities on Windows system, our team conducted first‐step research on them. We first classified file access control bugs into two types and codified some bug patterns. Then we formalized file access control vulnerabilities to propose a scalable detection method and implemented a lightweight analysis system StaticFAC. After evaluating StaticFAC in real‐world Windows software, we discovered 15 0‐day bugs.

Machine learning (ML) techniques are increasingly important in cybersecurity, as they can quickly analyse and identify different types of threats from millions of events. In spite of the increasing number of possible applications of ML, successful adoption of ML models in cybersecurity still highly relies on the explainability of those models that are used for making predictions. Explanations that support ML model outputs are crucial in cybersecurity-oriented ML applications because people need to get more information from the model than just binary output for analysis. The explainable models help ML developers solve the “trust” problem for a security application prediction in a faithful way: validating model behaviours, diagnosing misclassifications and sometimes automatically patching errors in the target models. Therefore, explainable ML for cybersecurity has become a necessary and important research branch. In this paper, we present the topic of explainable ML in cybersecurity through two general types of explanations: (1) ante hoc explanation, and (2) post hoc explanation, with their methodologies. We systematically review and categorise the state-of-the-art research, and provide comparative studies to help researchers find the optimal solutions to specific problems. We further list open issues in this field to facilitate future studies. This survey will benefit diverse groups of readers from both academia and industries, who want to effectively use ML to solve cybersecurity challenges.

This article demonstrates that nonmaximum suppression (NMS), which is commonly used in object detection (OD) tasks to filter redundant detection results, is no longer secure. Considering that NMS has been an integral part of OD systems, thwarting the functionality of NMS can result in unexpected or even lethal consequences for such systems. In this article, an adversarial example attack that triggers malfunctioning of NMS in OD models is proposed. The attack, namely, Daedalus, compresses the dimensions of detection boxes to evade NMS. As a result, the final detection output contains extremely dense false positives. This can be fatal for many OD applications, such as autonomous vehicles and surveillance systems. The attack can be generalized to different OD models, such that the attack cripples various OD applications. Furthermore, a way of crafting robust adversarial examples is developed by using an ensemble of popular detection models as the substitutes. Considering the pervasive nature of model reuse in real-world OD scenarios, Daedalus examples crafted based on an ensemble of substitutes can launch attacks without knowing the parameters of the victim models. The experimental results demonstrate that the attack effectively stops NMS from filtering redundant bounding boxes. As the evaluation results suggest, Daedalus increases the false positive rate in detection results to 99.9% and reduces the mean average precision scores to 0, while maintaining a low cost of distortion on the original inputs. It also demonstrates that the attack can be practically launched against real-world OD systems via printed posters.

Machine learning (ML) has been widely used for malware detection on different operating systems, including Android. To keep up with malware's evolution, the detection models usually need to be retrained periodically (e.g., every month) based on the data collected in the wild. However, this leads to poisoning attacks, specifically backdoor attacks, which subvert the learning process and create evasion ‘tunnels’ for manipulated malware samples. To date, we have not found any prior research that explored this critical problem in Android malware detectors. Although there are already some similar works in the image classification field, most of those similar ideas cannot be borrowed to solve this problem, because the assumption that the attacker has full control of the training data collection or labelling process is not realistic in real-world malware detection scenarios. In this article, we are motivated to study the backdoor attack against Android malware detectors. The backdoor is created and injected into the model stealthily without access to the training data and activated when an app with the trigger is presented. We demonstrate the proposed attack on four typical malware detectors that have been widely discussed in academia. Our evaluation shows that the proposed backdoor attack achieves up to 99 percent evasion rate over 750 malware samples. Moreover, the above successful attack is realised by a small size of triggers (only four features) and a very low data poisoning rate (0.3 percent).

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent years. However, most of the methods can only handle specific attacks. For example, proactive defending methods are invalid against grey-box or white-box attacks, while reactive defending methods are challenged by low-distortion adversarial examples or transferring adversarial examples. This becomes a critical problem since a defender usually does not have the type of attack asa prioriknowledge. Moreover, existing two-pronged defences (e.g., MagNet), which take advantage of both proactive and reactive methods, have been reported as broken under transferring attacks. To address this problem, this article proposed a novel defensive framework based on collaborative multi-task training, aiming at providing defence for different types of attacks. The proposed defence first encodes training labels into label pairs and counters black-box attacks leveraging adversarial training supervised by the encoded label pairs. The defence further constructs a detector to identify and reject high-confidence adversarial examples that bypass the black-box defence. In addition, the proposed collaborative architecture can prevent adversaries from finding valid adversarial examples when the defence strategy is exposed. In the experiments, we evaluated our defence against four state-of-the-art attacks on$MNIST$and$CIFAR10$datasets. The results showed that our defending method achieved up to 96.3 percent classification accuracy on black-box adversarial examples, and detected up to 98.7 percent of the high confidence adversarial examples. It only decreased the model accuracy on benign example classification by 2.1 percent for the$CIFAR10$dataset.

Coverage-guided fuzzing is one of the most effective solutions for vulnerability discovery. Among coverage-guided fuzzing, full-speed fuzzing, such as UnTracer, traces test cases only when they discover new coverage. Due to the high expense of tracing test cases, full-speed fuzzers improve the efficiency of fuzzing by tracing only coverage-increasing test cases. However, the existing full-speed fuzzer (i.e., UnTracer) is based on basic block coverage, suffering a severe problem called edge collision. Moreover, such fuzzers neglect the path frequency, which affects fuzzing effectiveness. In this article, we propose CSI-Fuzz, a fuzzer utilizing coverage sensitive instrumentation to address the problems of existing full-speed fuzzing. CSI-Fuzz directly instruments at edges, which solves the problem of edge collision. Meanwhile, CSI-Fuzz sets path identifiers to count the frequency of covered paths. Our CSI-Fuzz can be recognized as an add-on and seamlessly applied to existing coverage-guided fuzzers. We accordingly implement CSI-Fuzz based on two widely-adopted fuzzers, AFL and AFLFast, to evaluate its performance. The experiments demonstrate that CSI-Fuzz discovers more edges than AFL, AFLFast, and UnTracer. Additionally, CSI-Fuzz exposes more bugs than the other fuzzers.

With the development of 5G technology and Internet of Things, all kinds of real life data are collected and recorded by a large number of sensors. It is of great significance to mine and analyze the hidden information in the data for applications like future prediction. However, due to interferences or instability of collection equipment, collected sensory data are often incomplete, and this incompleteness hinders the in-depth analysis of data in the cloud. Therefore, processing around missing values is significant. Relying on cloud machine learning methods is not enough to deal with the problem of missing data in the Artificial Intelligence of Things (AIoT) environment, however, edge computing provides a promising solution. In this article, gated recurrent units filling is employed at the edge nodes. A mobile edge node can not only find the historical information of the current missing data node but also acquire the data of the nodes adjacent to the missing data node. These ensure that the missing data are restored to the maximum extent at the source. The experimental results show that the missing value filling based on edge computing not only outperforms other filling methods in quality but also greatly reduces the energy consumption in AIoT.

Edge computing, as a relatively recent evolution of cloud computing architecture, is the newest way for enterprises to distribute computational power and lower repetitive referrals to central authorities. In the edge computing environment, Generative Models (GMs) have been found to be valuable and useful in machine learning tasks such as data augmentation and data pre-processing. Federated learning and distributed learning refer to training machine learning models in the edge computing network. However, federated learning and distributed learning also bring additional risks to GMs since all peers in the network have access to the model under training. In this article, we study the vulnerabilities of federated GMs to data-poisoning-based backdoor attacks via gradient uploading. We additionally enhance the attack to reduce the required poisonous data samples and cope with dynamic network environments. Last but not least, the attacks are formally proven to be stealthy and effective toward federated GMs. According to the experiments, neural backdoors can be successfully embedded by including merely 5\% poisonous samples in the local training dataset of an attacker.

Computer users are generally faced with difficulties in making correct security decisions. While an increasingly fewer number of people are trying or willing to take formal security training, online sources including news, security blogs, and websites are continuously making security knowledge more accessible. Analysis of cybersecurity texts from this grey literature can provide insights into the trending topics and identify current security issues as well as how cyber attacks evolve over time. These in turn can support researchers and practitioners in predicting and preparing for these attacks. Comparing different sources may facilitate the learning process for normal users by creating the patterns of the security knowledge gained from different sources. Prior studies neither systematically analysed the wide range of digital sources nor provided any standardisation in analysing the trending topics from recent security texts. Moreover, existing topic modelling methods are not capable of identifying the cybersecurity concepts completely and the generated topics considerably overlap. To address this issue, we propose a semi-automated classification method to generate comprehensive security categories to analyse trending topics. We further compare the identified 16 security categories across different sources based on their popularity and impact. We have revealed several surprising findings as follows: (1) The impact reflected from cybersecurity texts strongly correlates with the monetary loss caused by cybercrimes, (2) security blogs have produced the context of cybersecurity most intensively, and (3) websites deliver security information without caring about timeliness much.

In mobile crowdsensing, many mobile devices are collectively used to complete complex sensing tasks. Most tasks require users to consume resources to ensure continuous performance over multiple periods of time. Therefore, it is important to incentivize enough users to continuously participate in the tasks. However, there are two issues with current incentive mechanisms. First, most studies are designed for maximizing the revenue of a single round of tasks rather than long-term incentives. Second, although some studies use historical data to design mechanisms for long-term operation, the law of diminishing marginal utility is not considered; thus, the actual performance is lower than expected. In this study, the concepts of capital deposit and intertemporal choice from behavioral economics are introduced to explain the principle of addiction, which is a representative long-term incentive. Consequently, an Addiction Incentive Mechanism (AIM) is proposed. It influences the utility and demand functions of users by accelerating the accumulation of capital deposits and promoting users to become addicted to cooperative behavior. It also mitigates the effect of diminishing marginal utility through intertemporal choice theory to maintain user engagement. Simulations demonstrate that AIM improves participation and repetition rates compared with the state-of-the-art mechanisms.

The proliferation of Internet of Things (IoT) devices has made people's lives more convenient, but it has also raised many security concerns. Due to the difficulty of obtaining and emulating IoT firmware, in the absence of internal execution information, black-box fuzzing of IoT devices has become a viable option. However, existing black-box fuzzers cannot form effective mutation optimization mechanisms to guide their testing processes, mainly due to the lack of feedback. In addition, because of the prevalent use of various and non-standard communication message formats in IoT devices, it is difficult or even impossible to apply existing grammar-based fuzzing strategies. Therefore, an efficient fuzzing approach with syntax inference is required in the IoT fuzzing domain.

While extremely valuable to achieve advanced functions, mobile phone sensors can be abused by attackers to implement malicious activities in Android apps, as experimentally demonstrated by many state-of-the-art studies. There is hence a strong need to regulate the usage of mobile sensors so as to keep them from being exploited by malicious attackers. However, despite the fact that various efforts have been put in achieving this, i.e., detecting privacy leaks in Android apps, we have not yet found approaches to automatically detect sensor leaks in Android apps. To fill the gap, we designed and implemented a novel prototype tool, Seeker, that extends the famous FlowDroid tool to detect sensor-based data leaks in Android apps. Seeker conducts sensor-focused static taint analyses directly on the Android apps' bytecode and reports not only sensor-triggered privacy leaks but also the sensor types involved in the leaks. Experimental results using over 40,000 real-world Android apps show that Seeker is effective in detecting sensor leaks in Android apps, and malicious apps are more interested in leaking sensor data than benign apps.

Deep Neural Networks (DNNs) are vulnerable to deliberately crafted adversarial examples. In the past few years, many efforts have been spent on exploring query-optimisation attacks to find adversarial examples of either black-box or white-box DNN models, as well as the defending countermeasures against those attacks. In this article, we explore vulnerabilities of DNN models under the umbrella of Man-in-the-Middle (MitM) attacks, which have not been investigated before. From the perspective of an MitM adversary, the aforementioned adversarial example attacks are not viable anymore. First, such attacks must acquire the outputs from the models multiple times before actually launching attacks, which is difficult for the MitM adversary in practice. Second, such attacks are one-off and cannot be directly generalised onto new data examples, which decreases the rate of return for the attacker. In contrast, using generative models to craft adversarial examples on the fly can mitigate the drawbacks. However, the adversarial capability of the generative models, such as Variational Auto-Encoder (VAE), has not been extensively studied. Therefore, given a classifier, we investigate using a VAE decoder to either transform benign inputs to their adversarial counterparts or decode outputs from benign VAE encoders to be adversarial examples. The proposed method can endue more capability to MitM attackers. Based on our evaluation, the proposed attack can achieve above 95 percent success rates on both MNIST and CIFAR10 datasets, which is better or comparable with state-of-the-art query-optimisation attacks. In the meantime, the attack is 104times faster than the query-optimisation attacks.

With the benefits of Internet of Vehicles (IoV) paradigm, come along unprecedented security challenges. Among many applications of inter-connected systems, vehicular networks and smart cars are examples that are already rolled out. Smart vehicles not only have networks connecting their internal components e.g. via Controller Area Network (CAN) bus, but also are connected to the outside world through road side units and other vehicles. In some cases, the internal and external network packets pass through the same hardware and are merely isolated by software defined rules. Any misconfiguration opens a window for the hackers to intrude into vehicles' internal components e.g. central lock system, Engine Control Unit (ECU), Anti-lock Braking System (ABS) or Adaptive Cruise Control (ACC) system. Compromise of any of these can lead to disastrous outcomes. In this paper, we study the security of smart vehicles' adaptive cruise control systems in the presence of covert attacks. We define two covert/stealth attacks in the context of cruise control and propose a novel intrusion detection and compensation method to disclose and respond to such attacks. More precisely, we focus on the covert cyber attacks that compromise the integrity of cruise controller and employ a neural network identifier in the IDS engine to estimate the system output dynamically and compare it against the ACC output. If any anomaly is detected, an embedded substitute controller kicks in and takes over the control. We conducted extensive experiments in MATLAB to evaluate the effectiveness of the proposed scheme in a simulated environment.

Users receive a multitude of security information in written articles, e.g., newspapers, security blogs, and training materials. However, prior research suggests that these delivery methods, including security awareness campaigns, mostly fail to increase people's knowledge about cyber threats. It seems that users find such information challenging to absorb and understand. Yet, to raise users' security awareness and understanding, it is essential to ensure the users comprehend the provided information so that they can apply the advice it contains in practice. We conducted a subjective study to measure the level of users' understanding of security texts. We find that 61% of the terms security experts used in their writings are hard for the public to understand, even for people with some IT backgrounds. We also observe that 88% of security texts have at least one such term. Moreover, we notice that existing dictionaries, including the online ones (e.g., Google Dictionary), cover no more than 35% of the terms found in security texts. To improve users' ability to understand security texts, we developed a framework to build a user-oriented security-centric dictionary from multiple sources. To evaluate the effectiveness of the dictionary, we developed a tool as a service to detect technical terms and explain their meanings to the user in pop-ups. The results of a subjective study to measure the tool's performance showed that it could increase users' ability to understand security articles by 30%.

Fuzzing has been a great success in discovering real-world complex programs vulnerabilities. However, fuzzing achieves this effect by blindly generating a large number of test cases, which undoubtedly contains a lot of meaningless mutation inputs. To solve the blindness, machine learning technology is applied to fuzzing in recent work. Some of the machine learning based methods focus on locating and mutating the key bytes in the input, but they do not pay attention to the characteristics in the field of fuzzing when they combine machine learning technology with fuzzing. In this paper, we implement a new fuzzer, called Speed-Neuzz, which uses neural networks to model the branch behaviours of the program based on accurate training data after mitigating the hash collision of AFL. Furthermore, SpeedNeuzz locates and mutates critical bytes in the program input with a gradient-based strategy as well as neighbor edge information. Taking the neighbor edge knowledge into account, we can further reduce the blindness of the mutation based on gradient information so that SpeedNeuzz can generate a large number of quality inputs. Experiments on several real-world programs prove that SpeedNeuzz can achieve higher edge coverage than the state-of-the-art fuzzer NEUZZ under the same time budget.

Blockchain brings opportunities and challenges for financial data sharing services. The essential properties in a distributed multi-parties system are data access control and privacy control. This paper proposes a hierarchical data access model for financial services, which contains consent management and dynamic credits management. We implement fine-grained data access control through rating accredited data recipients (ADRs). By accessing corresponding blockchain service logs, ADRs' credits will dynamically be updated. The credits evaluation algorithm is responsible for calculating ADRs' credits based on their completion rate, business ethics rate, and feedback positive rate. Moreover, through applying smart contracts, the efficiency of consent management can be improved, and privacy policies can be managed elastically. Finally, we deploy smart contracts on the Ethereum Rinkeby testnet to evaluate the model feasibility. Furthermore, the theoretical analysis and experimental results indicate that the prototype is secure and efficient.

The constantly increasing number of disclosed security vulnerabilities have become an important concern in the software industry and in the field of cybersecurity, suggesting that the current approaches for vulnerability detection demand further improvement. The booming of the open-source software community has made vast amounts of software code available, which allows machine learning and data mining techniques to exploit abundant patterns within software code. Particularly, the recent breakthrough application of deep learning to speech recognition and machine translation has demonstrated the great potential of neural models’ capability of understanding natural languages. This has motivated researchers in the software engineering and cybersecurity communities to apply deep learning for learning and understanding vulnerable code patterns and semantics indicative of the characteristics of vulnerable code. In this survey, we review the current literature adopting deep-learning-/neural-network-based approaches for detecting software vulnerabilities, aiming at investigating how the state-of-the-art research leverages neural techniques for learning and understanding code semantics to facilitate vulnerability discovery. We also identify the challenges in this new field and share our views of potential research directions.

Software vulnerability has long been an important but critical research issue in cybersecurity. Recently, the machine learning (ML)-based approach has attracted increasing interest in the research of software vulnerability detection. However, the detection performance of existing ML-based methods require further improvement. There are two challenges: one is code representation for ML and the other is class imbalance between vulnerable code and nonvulnerable code. To overcome these challenges, this article develops a DeepBalance system, which combines the new ideas of deep code representation learning and fuzzy-based class rebalancing. We design a deep neural network with bidirectional long short-term memory to learn invariant and discriminative code representations from labeled vulnerable and nonvulnerable code. Then, a new fuzzy oversampling method is employed to rebalance the training data by generating synthetic samples for the class of vulnerable code. To evaluate the performance of the new system, we carry out a series of experiments in a real-world ground-truth dataset that consists of the code from the projects of LibTIFF, LibPNG, and FFmpeg. The results show that the proposed new system can significantly improve the vulnerability detection performance. For example, the improvement is 15% in terms of F-measure.

Machine learning-based solutions have been successfully employed for the automatic detection of malware on Android. However, machine learning models lack robustness to adversarial examples, which are crafted by adding carefully chosen perturbations to the normal inputs. So far, the adversarial examples can only deceive detectors that rely on syntactic features (e.g., requested permissions, API calls,etc.), and the perturbations can only be implemented by simply modifying application’s manifest. While recent Android malware detectors rely more on semantic features from Dalvik bytecode rather than manifest, existing attacking/defending methods are no longer effective. In this paper, we introduce a new attacking method that generates adversarial examples of Android malware and evades being detected by the current models. To this end, we propose a method of applying optimal perturbations onto Android APK that can successfully deceive the machine learning detectors. We develop an automated tool to generate the adversarial examples without human intervention. In contrast to existing works, the adversarial examples crafted by our method can also deceive recent machine learning-based detectors that rely on semantic features such as control-flow-graph. The perturbations can also be implemented directly onto APK’s Dalvik bytecode rather than Android manifest to evade from recent detectors. We demonstrate our attack on two state-of-the-art Android malware detection schemes, MaMaDroid and Drebin. Our results show that the malware detection rates decreased from 96% to 0% in MaMaDroid, and from 97% to 0% in Drebin, with just a small number of codes to be inserted into the APK.

Fuzzing is a promising technique for detecting security vulnerabilities. Newly developed fuzzers are typically evaluated in terms of the number of bugs found on vulnerable programs/binaries. However, existing corpora usually do not capture the features that prevent fuzzers from finding bugs, leading to ambiguous conclusions on the pros and cons of the fuzzers evaluated. In this paper, we propose to address the above problem by generating corpora based on search-hampering features. As a proof-of-concept, we designed FEData, a prototype corpus that currently focuses on three search-hampering features to generate vulnerable programs for fuzz testing. Unlike existing corpora that can only answer "how", FEData can also further answer "why" by exposing (or understanding) the reasons for the identified weaknesses in a fuzzer. The "why" information serves as the key to the improvement of fuzzers. Based on the "why" information, our FEData programs enabled us to identify the weakness of AFLFast, called cycle explosion, behind. We further developed an improved version of AFLFast, called AFLFast+, which has overcome the cycle explosion problem. AFLFast+ retains the efficiency of AFLFast in path search while maintaining or even surpassing the bug-finding capability of AFL for the corpus evaluated.

Summary Studying the influence of negative words that spread during election period is an important work in social media. Most of current methods rely on sentiment analysis of tweets to determine the users' preference. However, sentiment analysis can only makes use of emotional words (ie, adverbs and adjectives), which only take 30 percent of the context in the Internet. According to our empirical analysis based on real datasets, the bias on word selection largely reduced the accuracy of the context in the Internet. In order to address this critical problem, we propose a new method that makes use of nouns with emotional context to determine the election preference of each user. By collecting the frequencies of words in context, we weigh the impact of each supportive/objective noun to strengthen the determination of users' preference. Final results will further be integrated to examine the effectiveness and efficiency of our proposed method. To indicate this idea, we collect and adopt real datasets (UK Prime Minister 2017 and US President Campaign 2016) in the experiments. All the experiment results suggested that our integrated method largely outperformed previous prediction methods. In particular, the prediction results were quite similar to the final results of the UK and US election. Meanwhile, for UK election, we found that the daily approval rate is closely related to the event happened everyday.

Fog computing, a paradigm that extends cloud computing and services to the edge of the network, meets enhanced requirements by locating data, computation power, and networking capabilities closer to end nodes. Fog computing is distinguished by its accessibility to end users, particularly its support for mobility. Fog nodes are geographically distributed and are deployed near wireless access points in areas with a significant usage. Fog devices may take the form of stand-alone servers or network devices with on-board computing capabilities. Services are hosted at the network edge or even within end-user devices, such as set-top boxes or access points. This reduces service latency, improves quality of service, and provides a superior experience for the user. Fog computing supports emerging Internet of Things (IoT) applications that demand real-time or predictable latency, such as industrial automation, transportation, and networks of sensors and actuators. Due to the capability to support a wide geographical distribution, fog computing is well positioned for real-time big data analytics. Fog supports densely distributed data collection points, adding a fourth axis to the often-mentioned big data dimensions (volume, variety, and velocity). Issues of security and privacy are in fog computing, but this remains understudied particularly in the design and implementation of fog computing; such solutions may not suit fog computing devices that are at the edges of networks. In such environments, fog computing devices face threats that do not arise in a well-managed cloud environment. The aim of this special issue in Concurrency and Computation Practice and Experience (CCPE) is to promote research and reflect the most recent advances of security and privacy issues in Fog computing. It includes invited, high-quality papers presented at the 9th International Symposium on Cyberspace Safety and Security (CSS 2017). This is also an open special issue where everyone is encouraged to submit papers. This special issue contains research papers addressing the state of the art technologies related to the security and privacy of fog computing. The set of accepted papers can be organised under the following key themes. Security has long been a critical but difficult problem to be addressed in the fog computing field. In this scheme, there are four high-quality papers accepted for publication in this special issue.1-4 First, Yu et al shared their survey work about services communication of Microservice-enabled Fog applications.1 Because a fog application based on Microservices architecture consists of numerous services and communication among services, they mainly focus on the security issues that arise in services communication of Microservices in four aspects: containers, data, permission, and network. Second, Zhao et al presented an IP geolocation method based on identification routers and local delay distribution similarity.2 IP geolocation is usually used in fog computing to avoid high latency and discriminate malicious requests by judging the location of users. Existing delay measurement-based IP geolocation approaches are not applicable to the network that has hierarchical topology and weak connectivity, and the precision of the classical Street-Level Geolocation (SLG) method will decrease dramatically when the common routers are anonymous. In this paper, the authors proposed an IP geolocation method based on identification routers and local delay distribution similarity to solve the IP geolocation problem in fog computing. Third, return-Oriented Programming (ROP) attacks become very popular in recent years as these attacks can bypass traditional defense mechanisms such as data execution prevention (DEP) effectively. Previous solutions suffer from limitations in that (1) some methods need to modify the target programs, (2) some methods introduce considerable performance cost, (3) some methods rely on the special hardware, and (4) most of existing methods could not provide an online protection for the target processes. In this paper, Tian et al presented OnRop, an on-the-fly ROP attack protection system by using the commodity hardware features and OS internal facilities.3 Their system is compatible with the existing programs, and its protection layer can be added on demand. Finally, Zhang et al proposed an algorithm to address the problems of latency in video denoising in fog computing environment. A series of measures has been applied in their algorithm, such as communication rate, and extremely heavy noise, structure registration, inter-frame and inner-frame filters, and distribution compensation. Privacy is another important issue in fog computing. In this scheme, there are also four accepted papers. First, Li et al proposed two practical approaches to implement a cloud-based DPI middlebox.5 The outsourced DPI middle-box performed payload inspection over encrypted traffic while preserving the privacy of both communication data and inspection rules. Second, Cao et al proposed an effective privacy-preserving scheme for electric load monitoring,6 which could guarantee differential privacy of data disclosure in smart grid. In the proposed scheme, an energy consumption behaviour model based on Factorial Hidden Markov Model (FHMM) is established. In addition, noise is added to the behaviour parameter, which is different from the traditional methods that usually add noise to the energy consumption data. Third, Zhou et al proposed effective methods to assist users to balance between the full control and the additional interaction burden,7 including sorting, recommendations, and establishing profiles. Finally, Zhang et al mainly focused on the privacy for Video Denoising.4 All these four papers have well introduced the latest research to the academia on addressing the privacy problem in fog computing. The next scheme is about the cryptography in fog computing. We accepted three papers for this scheme.8-10 First, Li et al proposed a verifiable chaotic encryption based on Chebyshev polynomials.8 The method supported verifiable function for data integrity. To further improve the efficiency of the method, a corresponding outsourced encryption method is constructed, where the heavy overhead evaluations of Chebyshev polynomials were transferred from the user side to the cloud server. The outsourced encryption also provided the checkability for data integrity and correctness of cloud computations. The method is suitable for mobile users with limited computing resources. Second, Bahrami et al proposed a novel hierarchical key pre-distribution method based on “Residual Design” for fog networks.9 The proposed key distribution method was designed to minimise storage overhead and memory consumption while increasing network scalability. The method was also designed to be secure against node capture attacks. Third, Wang et al proposed a new general pairing-free certificate-less signature method based on the variant of RSA problem and the discrete logarithm problem.10 As far as we know, this method was the first RSA-based certificate-less signature scheme that can possess resistance to Type I and Type II adversaries. There are also two papers that adopted blockchain techniques into Fog computing.11, 12 First, Huang et al proposed a new mechanism SeShare for data storing based on blockchain to realise signature uniqueness, which solved the problem of generating signatures for the same file meanwhile by different group users.11 Specifically, their method recorded every signature of a file in a blockchain in chronological order, and only one user was allowed to add new signature at the end of the blockchain when modification conflicts occurred. Second, Huang et al proposed a fair three-party contract signing protocol based on the primitive of blockchain, which could be applied to the scenario of fog computing.12 Their proposed construction allowed the participants to sign a contract in a fair way without the involvement of an arbitrator. Moreover, the privacy of the contract content could be preserved on the public chain. Their method also realised the proposed protocol through the private blockchain and provided the experimental simulation that analyses the efficiency and effectiveness. The articles presented in this special issue provides insights related to the security and privacy issues in fog computing, including blockchain-based techniques, cryptography, performance evaluation and improvements, and application developments. We wish the readers can benefit from insights of these papers, and contribute to these rapidly growing areas. Sheng Wen received his PhD degree from Deakin University, Melbourne, in October 2014. Currently, he has been working full-time as a senior lecturer (A/P in US) in Swinburne University of Technology. Before this, he first worked as a research fellow and then a Lecturer in Computer Science in the School of Information Technology at Deakin University from the year of 2015. Dr. Wen manages several research projects in the last three years. Since late 2014, Dr. Wen has received a large amount of funding from both academia and industries as co-/Chief Investigator (CI), including ARC Linkage Projects and CSRIO-Defence Joint Projects. Dr. Wen is now the Program Leader for System Security & Blockchain in Swinburne Cybersecurity Lab and Blockchain Innovation Lab. He is leading a medium-size research team in the system security area. This team includes Dr. Wen, eight Ph.D. students in Swinburne as co-/supervisors and three Honours students. Dr Wen has published over seventy fully-refereed papers in prestigious journals and leading conferences. He has also edited three books and seven journal special issues. In particular, Dr Wen has published forty fully refereed high-quality journal articles. Among these articles, fifteen articles are published in the most prestigious IEEE or ACM Transactions. Due to his outstanding performance in research, he was selected as the representative young scientist in Australia parliament (2015). Sheng is leading a blockchain project with Austrac to stop money laundering in Australia. The collaboration with Austrac is significant and has been reported in top blockchain related media like ‘Bitcoin’ website. He has also been selected as the cyber security expert in SBS channel to deliver security related knowledge and comment on security related event to the mass. His research impact not only contributes to his own academic reputation, but also promotes the reputation of Swinburne University in Australia. Aniello Castiglione received the Ph.D. degree in Computer Science from the University of Salerno, Italy. He is currently an Assistant Professor (tenured as Associate Professor) at the University of Naples “Parthenope,” Italy. Previously, he was Adjunct Professor at the University of Salerno, Italy, and at the University of Naples “Federico II.” He received the Italian national qualification as an Associate Professor of Computer Science. He published more than 210 papers in international journals and conferences. Considering his journal papers, more than 70 of them are ranked Q1 in Scopus/Scimago classification and more than 50 of them are ranked Q1 in the Clarivate Analytics/ISI-WoS classification. The international academic profile of Dr. Castiglione is spread among his 86 international co-authors who belong to 75 different institutions located in 18 countries. He served in the organization (mainly as the program chair and a TPC member) in around 230 international conferences (some of them are ranked A+/A/A- in the CORE, LiveSHINE, and Microsoft Academic international classifications). In 2014, one of his papers (published on the IEEE TDSC) has been selected as the Featured Article in the IEEE Cybersecurity Initiative. In 2018, another paper (published on the IEEE Cloud Computing) has been selected as the Featured Article in the IEEE Cloud Computing Initiative. He served as a reviewer for around 110 international journals and was the managing editor of two ISI-ranked international journals. He acted as a Guest Editor in around 20 special issues, including Future Generation Computer Systems (Elsevier), Information Sciences (Elsevier), Journal of Network and Computer Applications (Elsevier), Journal of Parallel and Distributed Computing (Elsevier), Computers & Security (Elsevier), Concurrency and Computation: Practice and Experience (Wiley), IEEE Communications Magazine, IEEE Access and served as an editor on around 10 editorial boards of international journals. His current research interests include Information Forensics, Digital Forensics, Security and Privacy on Cloud, Communication Networks, Applied Cryptography, and Sustainable Computing. Tian Wang received the B.Sc. and M.Sc. degrees in computer science from the Central South University, Changsha, China, in 2004 and 2007, respectively, and the Ph.D. degree in computer science from the City University of Hong Kong, Kowloon, Hong Kong, SAR, in 2011. He was a research assistant in the City University of Hong Kong from 2006-2008. He is currently an Associate Professor at the College of Computer Science and Technology, Huaqiao University, Xiamen, China. His research interests include wireless sensor networks, cloud computing, and fog computing. Dr. Wang manages several research projects such as the National Natural Science Foundation of China (NSFC). He has 2 patents and more than 70 technical publications in international conferences and journals in the areas of wireless sensor networks, cloud computing, and mobile computing. His papers have appeared in the prestigious journals/conferences in the domain, including IEEE TMC, IEEE TVT, ACM TOSN, Information Sciences, Computer networks, ACM Mobihoc, IEEE RTSS, IEEE MASS, IEEE ICC, and so on. He has served as publicity chair and program committee member of numerous international conferences. He serves as a publicity chair for IEEE DependSys 2016, session chair for SpaCCS 2016, track co-chair for IEEE CSS 2017, and program committee member of numerous international conferences (3PGCIC 2014, APSCC 2014, HPCC 2015, CoCoNet'15, ICA3PP 2015, WASA 2015, HPCC 2016, DependSys 2015, DependSys 2016). He is on the editorial board of International Journal of High-Performance Computing and Networking (IJHPCN). Md Zakirul Alam Bhuiyan is currently an Assistant Professor of Computer and Information Sciences at the Fordham University. Before that, he worked for Temple University USA. He also worked as a Postdoctoral Research Fellow in the School of Information Science and Engineering and the School of Software at Central South University, China. He received the Ph.D. degree and the MEng degree in Computer Science and Technology from Central South University (CSU), China, in 2013 and 2009, respectively. He received the BSc degree in Computer Science and Engineering from International Islamic University Chittagong, Bangladesh, in 2005. He is a key member of the Trusted Computing Institute of CSU, where his research interests lie in cyber-physical systems (CPS), wireless sensor network applications, fault-tolerance and reliability, and sensor-cloud computing. He was a Research Assistant at the Hong Kong Polytechnic University in 2010-2011 and a Software Engineer at international software companies. He was a recipient of a “Youth Scientific Fund 2015-2017” from NSF of China, “2012 Top-notch Ph.D. Student Award” from CSU, “2012 Hunan Province Innovative Engineering Research Fund Award,” and a recipient of the "Outstanding Master Degree Dissertation Award” at both the provincial and the university levels. His papers have appeared in the prestigious journals/conferences in the domain, including ACM TOSN, IEEE TC, IEEE TPDS, IEEE SECON, IEEE/IFIP DSN, IEEE SRDS, IEEE DCOSS, and so on. He won the “Best Paper Award” at the IEEE ISPA 2013, Melbourne, Australia, and the “Best Academic Paper Award 2012.” He was invited to serve as a Guest Editor, Workshop Chair, Publicity Chair, Program Co-Chair, TPC, and reviewer for international journal/conference proceedings. He is a member of IEEE and a member of ACM. We would like to thank all of the authors who provided valuable contributions to this special issue. We are also grateful to the Review Committee for the feedback provided to the authors, which are essential in further enhancing the papers. Finally, we would like to express our sincere gratitude to Professor Geoffrey Fox, the Editor in Chief, for providing us with this unique opportunity to present our works in the international journal of Concurrency and Computation: Practice and Experience.

Crowdsensing is a new paradigm of applications that takes advantage of mobile devices to collect sensing data. Tasks in crowdsensing will consume users' resources so that incentive mechanisms are necessary to encourage users' participation. Existing incentive mechanisms are based on traditional economics, which have two common problems: 1) the utility of different tasks is fungible and 2) users' behavioral preferences are consistent. Mental accounting (MA) theory in behavioral economics proves that the utility of tasks obtained in different ways is nonfungible and people's preferences of behavior are inconsistent. Reference dependence, loss aversion, and sensitivity decline are the three characteristics of MA. Reference dependence means people evaluate outcomes relative to a reference point, and then classify gains and losses. Loss aversion refers to people's tendency to prefer avoiding losses to acquiring equivalent gains. Sensitivity decline means that the marginal utility of MA about gains and losses is diminishing. Thus, this paper proposes an incentive mechanism called the MA auction incentive mechanism (MAAIM). Based on reference dependence, coupled with sensitivity decline, we establish an external reference environment and an internal reference point to motivate users. Based on loss aversion, we design a payment mechanism to encourage users to improve their data quality. The extensive simulation results show that MAAIM improves the number of users participating in sensing tasks, the utility of the sensing platform, and the quality of data collected by users.

Android users are increasingly concerned with the privacy of their data and security of their devices. To improve the security awareness of users, recent automatic techniques produce security-centric descriptions by performing program analysis. However, the generated text does not always address users’ concerns as they are generally too technical to be understood by ordinary users. Moreover, different users have varied linguistic preferences that do not match the text. Motivated by this challenge, we develop an innovative scheme to help users avoid malware and privacy-breaching apps by generating security descriptions that explain the privacy and security related aspects of an Android app in clear and understandable terms. We implement a prototype system, PERSCRIPTION, to generate personalised security-centric descriptions that automatically learn users’ security concerns and linguistic preferences to produce user-oriented descriptions. We evaluate our scheme through experiments and user studies. The results clearly demonstrate the improvement on readability and users’ security awareness of PERSCRIPTION’s descriptions compared to existing description generators.

As more and more people rely on social networks for business and life, social worms constitute one of the major security threats to our society. Modern social worms exhibit two new features,message notificationandthe temporal characteristic of human mobility. Message notification indicates a user will get a reminder once a new message comes to a social account. The temporal characteristic of human mobility indicates a user can operate corresponding computer in different locations with different resting time. Previous scholars have proposed some analytical models for the propagation dynamics of social worms. However, they did not consider the above two features and there is one critical problem unrealized, which isstructural imperfection of network topology. Previous models have not taken into account the hierarchical topology structure, which results from a many-to-many relationship between users and hosts. To address these problems, we model propagation dynamics of social worms oriented hierarchical networks in this paper, and the proposed model accurately describes the propagation behavior of social worms. We conduct both a theoretical analyses and extensive simulations to show our model can overcome inaccuracy in the number of infected nodes and provide a stronger approximation for the worm propagation. The results show that our model presented in this paper achieves a greater accuracy in characterizing the propagation of modern social worms.

Large-scale smart computing is generally more vulnerable to cyber attacks since their system devices are normally distributed as networked platforms and each device could be a target and get compromised. Due to resource constraints (i.e., Sustainable Computing demand) and cost-efficiency issues (i.e., Green Computing demand), we usually monitor only a few devices (i.e., partial observation) to ensure all operations across different platforms are under a secure environment. This leads to a critical problem for detecting compromised devices that are out of surveillance. To the best of our knowledge, this problem has not been solved so far. In this paper, we propose an unsupervised classifier based on source-tracing technique (STC in short) to expose hidden compromised devices with partial observation on the networked sustainable green smart computing platforms. STC mainly focuses on the cyber threats that can spread in the platform and compromise various system devices. To expose hidden compromised devices that are out-of-surveillance, STC first captures the spreading source by the reverse dissemination technique, and then relies on microscopic propagation modelling to probabilistically identify the most probable compromised devices. We carried out a series of experiments to validate the performance of our proposed method. The evaluations are based on three real networked platforms: Air Traffic Control system, AS-level Internet platform, and US Power Grid. The experiment results demonstrated that STC can accurately expose the hidden compromised devices in terms of following aspects: 1) Source-tracing (more than 80 percent runs got exact real source and 95 percent within two hops of real source); 2) Modelling (very close to the simulation results); 3) Exposing accuracy (almost all > 90 percent); and 4) Comparison to baseline (superiority to three supervised and two unsupervised classifiers).

Network inference has been extensively studied to better understand the information diffusion in online social networks. In this field, state-of- art widely adopted a priori knowledge related to users' infection timestamps. Researchers also assume that the smaller the time difference between two nodes, the higher the likelihood of an edge between the pair of users. However, according to our technical analyses and empirical studies, existing methods have two critical problems 1) alternative spreading paths; 2) users' delivery delay, which leads to the inaccuracy of previous methods. In this paper, we developed an innovative method to address the inference inaccuracy caused by the exposed two problems. This method determined the existence of an edge between a pair of users according to part of the users' features. The experiment results suggested that our method achieved around 70% accuracy in inferring network structures while existing methods failed in the same tasks.

Identifying rumor sources in social networks plays a critical role in limiting the damage caused by them through the timely quarantine of the sources. However, the temporal variation in the topology of social networks and the ongoing dynamic processes challenge our traditional source identification techniques that are considered in static networks. In this paper, we borrow an idea from criminology and propose a novel method to overcome the challenges. First, we reduce the time-varying networks to a series of static networks by introducing a time-integrating window. Second, instead of inspecting every individual in traditional techniques, we adopt a reverse dissemination strategy to specify a set of suspects of the real rumor source. This process addresses the scalability issue of source identification problems, and therefore dramatically promotes the efficiency of rumor source identification. Third, to determine the real source from the suspects, we employ a novel microscopic rumor spreading model to calculate the maximum likelihood (ML) for each suspect. The one who can provide the largest ML estimate is considered as the real source. The evaluations are carried out on real social networks with time-varying topology. The experiment results show that our method can reduce 60 - 90 percent of the source seeking area in various time-varying social networks. The results further indicate that our method can accurately identify the real source, or an individual who is very close to the real source. To the best of our knowledge, the proposed method is the first that can be used to identify rumor sources in time-varying social networks.

Accurate malware propagation modeling in wireless ad hoc networks (WANETs) represents a fundamental and open research issue which shows distinguished challenges due to complicated access competition, severe channel interference, and dynamic connectivity. As an effort towards the issue, in this paper, we investigate the malware propagation under two spread schemes including Unicast and Broadcast, in Spread Mode and Communication Mode, respectively. We highlight our contributions in three-fold in the light of previous literature works. First, a bound of malware infection rate for each scheme is provided by applying the wireless network capacity theories. Second, the impact of mobility on malware propagations has been studied. Third, discussion of the relationship between different schemes and practical applications is provided. Numerical simulations and detailed performance analysis show that the Broadcast Scheme with Spread Mode is most dangerous in the sense of malware propagation speed in WANETs, and mobility will greatly increase the risk further. The results achieved in this paper not only provide insights on the malware propagation characteristics in WANETs, but also serve as fundamental guidelines on designing defense schemes.

People are suffering from a range of risks in the ubiquitous networks of current world, such as rumours spreading in social networks, computer viruses propagating throughout the Internet and unexpected failures happened in Smart grids. We usually monitor only a few users of detecting various risks due to the resource constraints and privacy protection. This leads to a critical problem to detect compromised users who are out of surveillance. In this paper, we propose a risk assessment method to address this problem. The aim is to assess the security status of unmonitored users according to the limited information collected from monitored users in networks. There are two innovative techniques developed: First, we identify the source of risk propagation by inversely disseminating risks from the influenced (by rumours) or infected (by viruses) monitored users. We show a new finding that the ones who synchronously receive the risk copies from all monitored users are most likely to be the sources. Second, we propose a microscopic mathematical model to present the risk propagation from the exposed sources. This model forms a discriminant to classify the compromised users from others. For evaluations, we collect three real networks on which we launch simulated risk propagation and then sample the status of monitored users. The experiment results show that our method is effective and the result of risk assessment well matches the real status of the unmonitored users.

Summary Scale‐free networks are often used to model a wide range of real‐world networks, such as social, technological, and biological networks. Understanding the structure of scale‐free networks evolves into a big data problem for business, management, and protein function prediction. In the past decade, there has been a surge of interest in exploring the properties of scale‐free networks. Two interesting properties have attracted much attention: the assortative mixing and community structure. However, these two properties have been studied separately in either theoretical models or real‐world networks. In this paper, we show that the structural features of communities are highly related with the assortative mixing in scale‐free networks. According to the value of assortativity coefficient, scale‐free networks can be categorized into assortative, disassortative, and neutral networks, respectively. We systematically analyze the community structure in these three types of scale‐free networks through six metrics: node embeddedness, link density, hub dominance, community compactness, the distribution of community sizes, and the presence of hierarchical communities. We find that the three types of scale‐free networks exhibit significant differences in these six metrics of community structures. First, assortative networks present high embeddedness, meaning that many links lying within communities but few links lying between communities. This leads to the high link density of communities. Second, disassortative networks exhibit great hubs in communities, which results in the high compactness of communities that nodes can reach each other via short paths. Third, in neutral networks, a big portion of links act as community bridges, so they display sparse and less compact communities. In addition, we find that (dis)assortative networks show hierarchical community structure with power‐law‐distributed community sizes, while neutral networks present no hierarchy. Understanding the structure of communities from the angle of assortative mixing patterns of nodes can provide insights into the network structure and guide us in modeling information propagation in different categories of scale‐free networks. Copyright © 2016 John Wiley & Sons, Ltd.

Summary Twitter spam has long been a critical but difficult problem to be addressed. So far, researchers have developed a series of machine learning–based methods and blacklisting techniques to detect spamming activities on Twitter. According to our investigation, current methods and techniques have achieved the accuracy of around 87%. However, because of the problems of spam drift and information fabrication, these machine learning–based methods cannot efficiently detect spam activities in real‐life scenarios. Meanwhile, the blacklisting method also cannot catch up with the variations of spamming activities, as manually inspecting suspicious URLs is extremely timeconsuming. In this paper, we proposed a novel technique based on deep‐learning technique to address the above challenges. The syntax of each tweet will be learned through WordVector and trained by deep learning. We then constructed a binary classifier to differentiate spam and regular tweets. In experiments, we collected and labeled a 10‐day real tweet dataset as ground truth to evaluate our proposed method. We first went for empirical analysis with a series of comparisons to other methods: (1) performance of different classifiers, (2) other existing text‐based methods, and (3) nontext‐based detection techniques. According to the experiment results, our proposed method largely outperformed previous methods. We further conducted principle component analysis on typical methods to theoretically justify the outperformance of our method. We extracted all kinds of features via dimensionality reduction. It was found that our features were most distinct among all the detection methods. This well demonstrated the outperformance of our method.

Identifying influential spreaders in online social networks (OSNs) has long been an important but difficult problem to be addressed. Distinguished from previous works that mainly focused on the stationary features of users' influence, we systematically study the variations of users' spreading capability given the fact that influential spreaders are more likely to be the targets of various cyber attacks in real OSNs. In order to rank users' spreading capability, we adopt the k-shell structure which assigns a coreness index, ks, to each user. We find that users' spreading capability can considerably change when attacks occur in specific structures of OSNs. Generally, if the OSN structure is assortative (i.e., large-degree nodes preferably connect to nodes with large degree), users' spreading capability is resilient to attacks. However, if the OSN structure is disassortative (i.e., large-degree nodes preferably connect to nodes with small degree), users' spreading capability decreases significantly under attacks. We further carried out a series of empirical studies in real OSN datasets to disclose the causation of the variations caused by attacks. The research presented in this paper benefit decision makers to protect the propagation in the case of product promotion or prevent the diffusion like rumor.

Summary Fog computing is a paradigm that extends Cloud computing and services to the edge of the network. Similar to Cloud, Fog provides data, compute, storage and application services to end users. In this article, we elaborate the motivation and advantages of Fog computing and analyse its applications in a series of real scenarios, such as Smart Grid, smart traffic lights in vehicular networks and software defined networks. We discuss the state of the art of Fog computing and similar work under the same umbrella. Distinguished from other reviewing work of Fog computing, this paper further discloses the security and privacy issues according to current Fog computing paradigm. As an example, we study a typical attack, man‐in‐the‐middle attack, for the discussion of system security in Fog computing. We investigate the stealthy features of this attack by examining its CPU and memory consumption on Fog device. In addition, we discuss the authentication and authorization techniques that can be used in Fog computing. An example of authentication techniques is introduced to address the security scenario where the connection between Fog and Cloud is fragile. Copyright © 2015 John Wiley & Sons, Ltd.

Sensor networks are a branch of distributed ad hoc networks with a broad range of applications in surveillance and environment monitoring. In these networks, message exchanges are carried out in a multi-hop manner. Due to resource constraints, security professionals often use lightweight protocols, which do not provide adequate security. Even in the absence of constraints, designing a foolproof set of protocols and codes is almost impossible. This leaves the door open to the worms that take advantage of the vulnerabilities to propagate via exploiting the multi-hop message exchange mechanism. This issue has drawn the attention of security researchers recently. In this paper, we investigate the propagation pattern of information in wireless sensor networks based on an extended theory of epidemiology. We develop a geographical susceptible-infective model for this purpose and analytically derive the dynamics of information propagation. Compared with the previous models, ours is more realistic and is distinguished by two key factors that had been neglected before: 1) the proposed model does not purely rely on epidemic theory but rather binds it with geometrical and spatial constraints of real-world sensor networks and 2) it extends to also model the spread dynamics of conflicting information (e.g., a worm and its patch). We do extensive simulations to show the accuracy of our model and compare it with the previous ones. The findings show the common intuition that the infection source is the best location to start patching from, which is not necessarily right. We show that this depends on many factors, including the time it takes for the patch to be developed, worm/patch characteristics as well as the shape of the network.

Traditional tracking solutions in wireless sensor networks based on fixed sensors have several critical problems. First, due to the mobility of targets, a lot of sensors have to keep being active to track targets in all potential directions, which causes excessive energy consumption. Second, when there are holes in the deployment area, targets may fail to be detected when moving into holes. Third, when targets stay at certain positions for a long time, sensors surrounding them have to suffer heavier work pressure than do others, which leads to a bottleneck for the entire network. To solve these problems, a few mobile sensors are introduced to follow targets directly for tracking because the energy capacity of mobile sensors is less constrained and they can detect targets closely with high tracking quality. Based on a realistic detection model, a solution of scheduling mobile sensors and fixed sensors for target tracking is proposed. Moreover, the movement path of mobile sensors has a provable performance bound compared to the optimal solution. Results of extensive simulations show that mobile sensors can improve tracking quality even if holes exist in the area and can reduce energy consumption of sensors effectively.

Abstract Locating the real source of the Internet attacks has long been an important but difficult problem to be addressed. In the real world, attackers can easily hide their identities and evade punishment by relaying their attacks through a series of compromised systems or devices called stepping stones. Currently, researchers mainly use similar features from the network traffic, such as packet timestamps and frequencies, to detect stepping stones. However, these features can be easily destroyed by attackers using evasive techniques. In addition, it is also difficult to implement an appropriate threshold of similarity that can help justify the stepping stones. In order to counter these problems, in this paper, we introduce the consistent causality probability to detect the stepping stones. We formulate the ranges of abnormal causality probabilities according to the different network conditions, and on the basis of it, we further implement to self‐adaptive methods to capture stepping stones. To evaluate our proposed detection methods, we adopt theoretic analysis and empirical studies, which demonstrate accuracy of the abnormal causality probability. Moreover, we compare our proposed methods with previous works. The result shows that our methods in this paper significantly outperform previous works in the accuracy of detection malicious stepping stones, even when evasive techniques are adopted by attackers. Copyright © 2014 John Wiley & Sons, Ltd.

Online social networks (OSN) have become one of the major platforms for people to exchange information. Both positive information (e.g., ideas, news and opinions) and negative information (e.g., rumors and gossips) spreading in social media can greatly influence our lives. Previously, researchers have proposed models to understand their propagation dynamics. However, those were merely simulations in nature and only focused on the spread of one type of information. Due to the human-related factors involved, simultaneous spread of negative and positive information cannot be thought of the superposition of two independent propagations. In order to fix these deficiencies, we propose an analytical model which is built stochastically from a node level up. It can present the temporal dynamics of spread such as the time people check newly arrived messages or forward them. Moreover, it is capable of capturing people’s behavioral differences in preferring what to believe or disbelieve. We studied the social parameters impact on propagation using this model. We found that some factors such as people’s preference and the injection time of the opposing information are critical to the propagation but some others such as the hearsay forwarding intention have little impact on it. The extensive simulations conducted on the real topologies confirm the high accuracy of our model.

The global diffusion of epidemics, computer viruses, and rumors causes great damage to our society. It is critical to identify the diffusion sources and timely quarantine them. However, most methods proposed so far are unsuitable for diffusion with multiple sources because of the high computational cost and the complex spatiotemporal diffusion processes. In this paper, based on the knowledge of infected nodes and their connections, we propose a novel method to identify multiple diffusion sources, which can address three main issues in this area: 1) how many sources are there? 2) where did the diffusion emerge? and 3) when did the diffusion break out? We first derive an optimization formulation for multi-source identification problem. This is based on altering the original network into a new network concerning two key elements: 1) propagation probability and 2) the number of hops between nodes. Experiments demonstrate that the altered network can accurately reflect the complex diffusion processes with multiple sources. Second, we derive a fast method to optimize the formulation. It has been proved that the proposed method is convergent and the computational complexity is O(mn logα), where α = α(m, n) is the slowly growing inverse-Ackermann function, n is the number of infected nodes, and m is the number of edges connecting them. Finally, we introduce an efficient algorithm to estimate the spreading time and the number of diffusion sources. To evaluate the proposed method, we compare the proposed method with many competing methods in various real-world network topologies. Our method shows significant advantages in the estimation of multiple sources and the prediction of spreading time.

Abstract—Fog Computing is a paradigm that extends Cloud computing and services to the edge of the network. Similar to Cloud, Fog provides data, compute, storage, and application services to end-users. In this article, we elaborate the motivation and advantages of Fog computing, and analyse its applications in a series of real scenarios, such as Smart Grid, smart traffic lights in vehicular networks and software defined networks. We discuss the state-of-the-art of Fog computing and similar work under the same umbrella. Security and privacy issues are further disclosed according to current Fog computing paradigm. As an example, we study a typical attack, man-in-the-middle attack, for the discussion of security in Fog computing. We investigate the stealthy features of this attack by examining its CPU and memory consumption on Fog device.

Due to the critical security threats imposed by email-based malware in recent years, modeling the propagation dynamics of email malware becomes a fundamental technique for predicting its potential damages and developing effective countermeasures. Compared to earlier versions of email malware, modern email malware exhibits two new features, reinfection and self-start. Reinfection refers to the malware behavior that modern email malware sends out malware copies whenever any healthy or infected recipients open the malicious attachment. Self-start refers to the behavior that malware starts to spread whenever compromised computers restart or certain files are visited. In the literature, several models are proposed for email malware propagation, but they did not take into account the above two features and cannot accurately model the propagation dynamics of modern email malware. To address this problem, we derive a novel difference equation based analytical model by introducing a new concept of virtual infected user. The proposed model can precisely present the repetitious spreading process caused by reinfection and self-start and effectively overcome the associated computational challenges. We perform comprehensive empirical and theoretical study to validate the proposed analytical model. The results show our model greatly outperforms previous models in terms of estimation accuracy.

Restraining the spread of rumors in online social networks (OSNs) has long been an important but difficult problem to be addressed. Currently, there are mainly two types of methods 1) blocking rumors at the most influential users or community bridges, or 2) spreading truths to clarify the rumors. Each method claims the better performance among all the others according to their own considerations and environments. However, there must be one standing out of the rest. In this paper, we focus on this part of work. The difficulty is that there does not exist a universal standard to evaluate them. In order to address this problem, we carry out a series of empirical and theoretical analysis on the basis of the introduced mathematical model. Based on this mathematical platform, each method will be evaluated by using real OSN data. We have done three types of analysis in this work. First, we compare all the measures of locating important users. The results suggest that the degree and betweenness measures outperform all the others in the Facebook network. Second, we analyze the method of the truth clarification method, and find that this method has a long-term performance while the degree measure performs well only in the early stage. Third, in order to leverage these two methods, we further explore the strategy of different methods working together and their equivalence. Given a fixed budget in the real world, our analysis provides a potential solution to find out a better strategy by integrating both types of methods together. From both the academic and technical perspective, the work in this paper is an important step towards the most practical and optimal strategies of restraining rumors in OSNs.

Social network worms, such as email worms and facebook worms, pose a critical security threat to the Internet. Modeling their propagation dynamics is essential to predict their potential damages and develop countermeasures. Although several analytical models have been proposed for modeling propagation dynamics of social network worms, there are two critical problems unsolved: temporal dynamics and spatial dependence. First, previous models have not taken into account the different time periods of Internet users checking emails or social messages, namely, temporal dynamics. Second, the problem of spatial dependence results from the improper assumption that the states of neighboring nodes are independent. These two problems seriously affect the accuracy of the previous analytical models. To address these two problems, we propose a novel analytical model. This model implements a spatial-temporal synchronization process, which is able to capture the temporal dynamics. Additionally, we find the essence of spatial dependence is the spreading cycles. By eliminating the effect of these cycles, our model overcomes the computational challenge of spatial dependence and provides a stronger approximation to the propagation dynamics. To evaluate our susceptible-infectious-immunized (SII) model, we conduct both theoretical analysis and extensive simulations. Compared with previous epidemic models and the spatial-temporal model, the experimental results show our SII model achieves a greater accuracy. We also compare our model with the susceptible-infectious-susceptible and susceptible-infectious- recovered models. The results show that our model is more suitable for modeling the propagation of social network worms.

Email worms propagate across networks by taking advantage of email relationships. Modeling the propagation of email worms can help predict their potential damages and develop countermeasures. We propose a novel analytical model on the propagation process of modern reinfection email worms. It relies on probabilistic analysis, and thus can provide a steady and reliable assessment on the propagation dynamics. Additionally, by introducing virtual users to represent the repetitious spreading process, the proposed model overcomes the computational challenge caused by reinfection processes. To demonstrate the benefits of our model, we conduct a series of experimental evaluation. The results show that our novel approach achieves a greater accuracy and is more suitable for modeling modern email worms than previous models.

SUMMARY In this paper, we present some practical experiences on implementing an alert fusion mechanism from our project. After investigation on most of the existing alert fusion systems, we found the current body of work alternatively weighed down in the mire of insecure design or rarely deployed because of their complexity. As confirmed by our experimental analysis, unsuitable mechanisms could easily be submerged by an abundance of useless alerts. Even with the use of methods that achieve a high fusion rate and low false positives, attack is also possible. To find the solution, we carried out analysis on a series of alerts generated by well‐known datasets as well as realistic alerts from the Australian Honey‐Pot. One important finding is that one alert has more than an 85% chance of being fused in the following five alerts. Of particular importance is our design of a novel lightweight Cache‐based Alert Fusion Scheme, called CAFS. CAFS has the capacity to not only reduce the quantity of useless alerts generated by intrusion detection system, but also enhance the accuracy of alerts, therefore greatly reducing the cost of fusion processing. We also present reasonable and practical specifications for the target‐oriented fusion policy that provides a quality guarantee on alert fusion, and as a result seamlessly satisfies the process of successive correlation. Our experiments compared CAFS with traditional centralized fusion. The results showed that the CAFS easily attained the desired level of simple, counter‐escapable alert fusion design. Furthermore, as a lightweight scheme, CAFS can easily be deployed and excel in a large amount of alert fusions, which go towards improving the usability of system resources. To the best of our knowledge, our work is a practical exploration in addressing problems from the academic point of view. Copyright © 2011 John Wiley & Sons, Ltd.

There are the two common means for propagating worms: scanning vulnerable computers in the network and sending out malicious email attachments. Modeling the propagation of worms can help us understand how worms spread and devise effective defence strategies. Most traditional models simulate the overall scale of infected network in each time tick, making them invalid for examining deep inside the propagation procedure among individual nodes. For this reason, this paper proposes a novel probability matrix to model the propagation mechanism of the two main classes of worms (scanning and email worms) by concentrating on the propagation probability. The objective of this paper is to access the spreading and work out an effective scheme against the worms. In order to evaluate the effects of each major component in our probability model, we implement a series of experiments for both worms. From the results, the network administrators can make decision on how to reduce the number of vulnerable nodes to a certain threshold for scanning worms, and how to immunize the highly-connected node for preventing worm's propagation for email worms.

Each year, large amounts of money and labor are spent on patching the vulnerabilities in operating systems and various popular software to prevent exploitation by worms. Modeling the propagation process can help us to devise effective strategies against those worms’ spreading. This paper presents a microcosmic analysis of worm propagation procedures. Our proposed model is different from traditional methods and examines deep inside the propagation procedure among nodes in the network by concentrating on the propagation probability and time delay described by a complex matrix. Moreover, since the analysis gives a microcosmic insight into a worm's propagation, the proposed model can avoid errors that are usually concealed in the traditional macroscopic analytical models. The objectives of this paper are to address three practical aspects of preventing worm propagation: (i) where do we patch? (ii) how many nodes do we need to patch? (iii) when do we patch? We implement a series of experiments to evaluate the effects of each major component in our microcosmic model. Based on the results drawn from the experiments, for high-risk vulnerabilities, it is critical that networks reduce the number of vulnerable nodes to below 80%. We believe our microcosmic model can benefit the security industry by allowing them to save significant money in the deployment of their security patching schemes.

In this paper, we present some practical experience on implementing an alert fusion mechanism from our project. After investigation on most of the existing alert fusion systems, we found the current body of work alternatively weighed down in the mire of insecure design or rarely deployed because of their complexity. As confirmed by our experimental analysis, unsuitable mechanisms could easily be submerged by an abundance of useless alerts. Even with the use of methods that achieve a high fusion rate and low false positives, attack is also possible. To find the solution, we carried out analysis on a series of alerts generated by well-known datasets as well as realistic alerts from the Australian Honey-Pot. One important finding is that one alert has more than an 85% chance of being fused in the following 5 alerts. Of particular importance is our design of a novel lightweight Cache-based Alert Fusion Scheme, called CAFS. CAFS has the capacity to not only reduce the quantity of useless alerts generated by IDS (Intrusion Detection System), but also enhance the accuracy of alerts, therefore greatly reducing the cost of fusion processing. We also present reasonable and practical specifications for the target-oriented fusion policy that provides a quality guarantee on alert fusion, and as a result seamlessly satisfies the process of successive correlation. Our experimental results showed that the CAFS easily attained the desired level of survivable, inescapable alert fusion design. Furthermore, as a lightweight scheme, CAFS can easily be deployed and excel in a large amount of alert fusions, which go towards improving the usability of system resources. To the best of our knowledge, our work is a novel exploration in addressing these problems from a survivable, inescapable and deployable point of view.

Distributed denial of service (DDoS) attack is a continuous critical threat to the Internet. Derived from the low layers, new application-layer-based DDoS attacks utilizing legitimate HTTP requests to overwhelm victim resources are more undetectable. The case may be more serious when such attacks mimic or occur during the flash crowd event of a popular Website. In this paper, we present the design and implementation of CALD, an architectural extension to protect Web servers against various DDoS attacks that masquerade as flash crowds. CALD provides real-time detection using mess tests but is different from other systems that use resembling methods. First, CALD uses a front-end sensor to monitor the traffic that may contain various DDoS attacks or flash crowds. Intense pulse in the traffic means possible existence of anomalies because this is the basic property of DDoS attacks and flash crowds. Once abnormal traffic is identified, the sensor sends ATTENTION signal to activate the attack detection module. Second, CALD dynamically records the average frequency of each source IP and check the total mess extent. Theoretically, the mess extent of DDoS attacks is larger than the one of flash crowds. Thus, with some parameters from the attack detection module, the filter is capable of letting the legitimate requests through but the attack traffic stopped. Third, CALD may divide the security modules away from the Web servers. As a result, it keeps maximum performance on the kernel web services, regardless of the harassment from DDoS. In the experiments, the records from www.sina.com and www.taobao.com have proved the value of CALD.