Large language model (LLM)-driven agents are designed to handle a wide range of tasks autonomously. As tasks become increasingly composite, the integration of multiple agents into a graph-structured system offers a promising solution. Recent advances mainly architect the communication order among agents into a specified directed acyclic graph, from which a one-by-one execution can be determined by topological sort. However, sequential architectures restrict the diversity of the information flow, hinder parallel computation, and exhibit vulnerabilities to potential backdoor threats. To overcome underlying shortcomings of sequential structures, we propose a node-wise multi-agent scheme, named message passing agent system (MPAS). Specifically, to parallelize the communication across agents, we extend the message propagation mechanism in graph representation learning to multi-agent scenarios and introduce our individual-epistemic message propagation. To further enhance expressiveness and robustness, we investigate three self-driven message aggregators. To achieve desired working flows, collaborative connections can be optimized without constraints. The experimental results reveal that compared to state-of-the-art sequential designs, MPAS could architect more advanced algorithms in 93.8% of the evaluations, reduce the average communication time from 84.6 seconds to 14.2 seconds per round on AQuA, and improve resilience against backdoor misinformation injection in 94.4% tests.

Cyberworthiness, as it is termed in Australian Defence, is a necessary feature of modern complex systems that are required to operate in a hostile cyber environment. To evaluate the cyberworthiness of complex systems or system-of-systems, the researchers developed a Cyber Evaluation and Management Toolkit (CEMT) which leverages model-based systems engineering techniques to examine a cyber-physical system’s vulnerability to, and risk of, cyber-attacks. This assessment method addresses the cyber-attack surface and threat kill chains, including supply chains and supporting infrastructure. Our previous research developing the CEMT is summarised, and the research results of a major implementation trial on a naval capability are presented. CEMT is novel to other similar assessment approaches articulated in the literature research by being threat-led and using visualisations tailored to inform decision-makers without specific cyber expertise. The research trial found strong support among all categories of stakeholders that CEMT improved the rigour in determining complex system vulnerabilities, ranking the likely cyber risks, and proposing the most appropriate mitigations to reinforce and pursue as applicable. 62.5% of trial respondents gave the CEMT a qualitative rating of Excellent or Very Good , and the recommendation likelihood mean across all respondents was 8.6 out of 10. Moreover, the assessment approach left a sound basis to maintain an informed accreditation against future cyber-threats and system changes. This large and lengthy case study on a major Defence platform provides a clear indication of suitability for further trials of the CEMT when evaluating and assessing the cyberworthiness of complex cyber-physical systems.

The pre-training multimodal models have achieved remarkable success with powerful cross-modal understanding capabilities, while easily being affected by deliberate injection attacks. Although the deceptive injection attacks are harmful, they are valuable in revealing the vulnerability and improving the robustness for multimodal models. Unfortunately, the existing multimodal injection attacks pay less attention to the complicated roles of different modality-related causal correlation, which results in such attacks being susceptible to detection and defense. To alleviate this issue, we propose a novel specious malignant injection attack framework, calledSMInject, which exploits both the irrationality and causal correlation across diverse modalities to stealthily manipulate the space of output. To enhance the stealthiness, we generate deceptive injections to assemble the concepts by analyzing causal correlation under four types of attacks. To further boost the effectiveness, the malignant injections are guided to penetrate in the encoded embedding space by designing the premise-hypothesis consensus alignment. Extensive experiments on representative multimodal models demonstrate that ourSMInjectachieves over 14% higher attack success rate and 6% higher Hit@5 metric than state-of-the-art methods while preserving the overall utility of models. Moreover, we highlight that theSMInjectalso exhibits the desired transferability by investigating the impact of contextual factors, such as similar attack profiles, imperceptible noise perturbations,etc. Our code is available athttps://anonymous.4open.science/r/SMInject-0DBC.

Unlike standard vulnerability disclosure, fixing vulnerabilities "silently" is another common approach in software development. While silent fixes can prevent potential targeted attacks without disclosing any details, they only offer short-term protection. Users often rely on publicly disclosed vulnerabilities to identify and eliminate vulnerabilities in their own software, particularly for open-source software (OSS). We conduct the first comprehensive empirical study in OSS to investigate potential security threats brought by silent fixes. By examining disclosed vulnerabilities and their corresponding patches in real-world OSSes, we investigated the prevalence of silent vulnerabilities and assessed the potential impacts they might cause. After analyzing 3,515 vulnerabilities, we observed that nearly 50% of the vulnerabilities, with half of them classified as high-severity, were exposed for over 30 days. Over 10% of them published exploits during the "silent" period, enabling adversaries to replicate the exploits and attack other OSS users. Due to delayed vulnerability disclosure, we even found one HIGH-severity vulnerability that was silently fixed still exists in downstream software, indicating that silent fixes may increase the risks for other OSSes, amplifying their impact throughout software supply chains.

The past decade has witnessed the wide adoption of AI code generators, such as GitHub Copilot, AskCodi, and OpenAI Codex. They offer intelligent solution code for code completion to achieve faster development, cleaner code, and a significant boost in overall productivity. However, such significant productivity advantages also inadvertently lead to the generation of insecure solution code because most AI code generators derive their knowledge from existing projects, which typically prioritize functionality over security. Although numerous tools have been developed to integrate with the code generators for identifying vulnerabilities, the inconsistency in syntactic features and variability in coding rules make the detection task challenging across different programming languages. To address the challenges, we devise a prompt-enhancing approach, PECKER. It examines textual prompts provided by users to identify risky prompts that could lead to insecure code generation. Given the risky prompts, PECKER conducts security-centric rewriting to strengthen the "potentially insecure" descriptions, thereby guiding AI code generators in mitigating vulnerabilities during code generation. We integrated PECKER with one of the most prevalent AI code generators, GitHub Copilot for evaluation. Among 509 risky prompts, PECKER successfully identified and rectified 471 risky prompts.

Manufacturers offer adjustable control parameters for flight control systems to accommodate diverse environments and missions. To ensure flight safety, they also develop established boundaries, i.e., range specifications for parameter values. However, even when the configuration parameters fall within the prescribed manufacturer range, they could still lead to instability or even severe incidents like crashes, which are referred to asRange Specification Bugs. Prior research has suggested shrinking the range of parameter values to protect drones from the adverse effects of such bugs. However, narrowing the range of parameters may only reduce the probability of errors and could potentially limit the drone’s adaptability. To overcome this limitation, we present an online approach that analyzes a sequence of flight states to detect any potential triggering of bugs and rectify the drone by dynamically adjusting its parameters. We implemented the rectification approach,ConFix, and applied it in current prevalent flight control systems, Ardupilot and PX4. The results demonstrated thatConFixachieved an average rectification success rate of 80%.

There have been significant improvements in intellectual property (IP) protection for deep learning models trained on euclidean data. However, the complex and irregular graph-structured data in non-euclidean space poses a huge challenge to the IP protection of graph neural networks (GNNs). To address this issue, we propose a subtle and interactive GNN fingerprinting scheme through spatial structure inference perturbation, which captures the stable coordination patterns of fingerprint to guarantee the reliability of copyright verification. Specifically, the data augmentation based on adaptive graph diffusion is first exploited to generate more samples, which enables the exploration of fingerprint information from coarse to fine. Subsequently, the graph-structured data are manipulated by multi-constrained spectral clustering to analyze intrinsic and extrinsic structure correlations in a causal inference manner. Ultimately, the cycle-consistent statistical optimization is performed to determine the copyright of GNN models from both intra-graph and inter-graph perspectives. Extensive experiments show that our proposed scheme can effectively verify the IP of GNN models on various challenging graph-structured datasets. Furthermore, we reveal that the space causality inference can facilitate the acquisition of inherent structural information, which improves the quality and robustness of the fingerprint under model modification operations and other model stealing attacks.

With the rapid development of mobile apps, developers tend to implement a variety of functionalities to support users’ demands. Thus, they involve the usage of native libraries to fulfill the luxuriant functionalities and maintain fast system responses, instead of using a unitary programming language (i.e., Java). Nonetheless, such an inter-language programming framework also introduces more security issues because attackers can conceal malicious behaviors at the native level to evade Android security vetting. Existing state-of-the-art detection tools mainly rely on the information extracted in the Java code to infer the potential malicious behaviors implemented in native code. None of them could simultaneously study the correlated behaviors in Java and native code. Therefore, in this paper, we proposed a static semantic-driven malware detection tool,GNNDroid, to distinguish malware by combining the behaviors implemented in both Java and native code. First,GNNDroidseparately analyzes Java and native code to construct Java function call graphs and native function call graphs. It then utilizes a regex-based function recognition approach to explore the correlations between Java code and native code. According to the code correlations,GNNDroidconstructs Multi-Relational Directed Graphs (MRDGs) to extract the comprehensive behaviors. Finally, it executes a Gated Graph Neural Network (GGNN) to analyze the MRDGs and distinguish malicious apps. We assessedGNNDroidby analyzing 40,000 Android apps and compared them with state-of-the-art tools. The result demonstrated thatGNNDroidnot only performs well when analyzing Java+native apps (i.e., apps implemented by both Java and native code), achieving an F1 of 98.57% but also effectively exploits Java only apps (i.e., apps implemented by Java code), achieving an F1 of 96.31%.

Perturbation-based privacy-preserving truth discovery requires the Service Provider (SP) to calculate the truthful aggregation result from perturbed data of the Data Sources (DSs), which inevitably damages the aggregation accuracy due to perturbation noise added in the data. Thus, the existing works attempt to relieve the perturbation errors by reducing noise amounts or adjusting aggregation weights of DSs. However, the former sacrifices DSs' privacy preservation and the latter has the limited accuracy recovery performance. Aiming at it, we propose an accuracy-enabling differential privacy-preserving truth discovery consisting of an independence-guaranteed data perturbation module and a progressive-private noise elimination module. Specifically, in the first module, SP generates mass of noises following DS's desired perturbation parameters and DS privately obtains one of noise based on private information retrieval. Meanwhile, to realize the perturbation's traceability, SP preserves the ciphertext of DSs' acquired noises, assisting the following noise elimination. In the second module, SP first removes his preserved DS's encrypted noise from perturbed truth according to homomorphic encryption, and then requires DS to decrypt this cleaned truth. The above two processes are progressively and iteratively implemented until all DSs have been involved. Theoretical analysis shows that our scheme can protect DSs' raw data privacy in both truth discovery process and noise elimination process. Extensive experiments using the real-world dataset demonstrate that our scheme can effectively eliminate more than 90% of the perturbation noise effects on the truth discovery accuracy.

Graph neural networks (GNNs) have gained increasing popularity in understanding graph-structured data due to their ability to derive meaningful representations by aggregating complicated topological information. However, privacy operations such as differential privacy mechanisms that inject noise into node features or graph structures to protect sensitive information, and distribution shifts in graph data pose tremendous security risks for the wide application of GNN models. Current researches mainly focus on defending the out-of-distribution (OOD) attacks through robust adversarial training and graph structure purification. Nonetheless, privacy perturbations of graph structures may render OOD attacks more deceptive by obfuscating the distinctiveness of nodes, leading to the failure of existing defense methods. To address these shortcomings, we propose an environment-adaptive representation interaction (EARI) scheme that strengthens the privacy perception of GNNs. Specifically, our scheme leverages the interaction between non-private and private data to enable targeted embedding propagation by the guidance of confidence score feedback. Subsequently, the representation-enriched topological aggregation is implemented to capture more discriminative features by exploiting multi-hop neighborhoods rather than stacked multilayers. Finally, the generalization-enhanced cluster-wise adaptation learning is leveraged to highlight the invariant correlations from nodes across different environments. Extensive experimental results demonstrate that our scheme can enhance the capability of learning representations from privacy-protected graph data, enabling GNNs to effectively defend against deceptive OOD attacks on various graph-structured datasets. Moreover, we reveal that the utilization of interactive topological aggregation can extremely enrich the diversity and guarantee the effectiveness for graph representations.

Reconstruction attacks against federated learning (FL) aim to reconstruct users’ samples through users’ uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample reconstruction in FL, where gradients are clipped and perturbed. Existing attacks are ineffective in FL with LDP since clipped and perturbed gradients obliterate most sample information for reconstruction. Besides, existing attacks embed additional sample information into gradients to improve the attack effect and cause gradient expansion, leading to a more severe gradient clipping in FL with LDP. In this paper, we propose a sample reconstruction attack against LDP-based FL with any target models to reconstruct victims’ sensitive samples to illustrate that FL with LDP is not flawless. Considering gradient expansion in reconstruction attacks and noise in LDP, the core of the proposed attack is gradient compression and reconstructed sample denoising. For gradient compression, an inference structure based on sample characteristics is presented to reduce redundant gradients against LDP. For reconstructed sample denoising, we artificially introduce zero gradients to observe noise distribution and scale confidence interval to filter the noise. Theoretical proof guarantees the effectiveness of the proposed attack. Evaluations show that the proposed attack is the only attack that reconstructs victims’ training samples in LDP-based FL and has little impact on the target model’s accuracy. We conclude that LDP-based FL needs further improvements to defend against sample reconstruction attacks effectively.

Configurations are supported by most flight control systems, allowing users to control a flying drone adapted to complexities such as environmental changes or mission alterations. Such an advanced functionality also introduces a significant problem—misconfiguration settings. It may cause drone instability, threaten drone safety, and potentially lead to substantial financial loss. However, detecting and rectifying misconfigurations across different flight control systems is challenging because (1) (mis)configuration-related code snippets might be syntactically correct and thus hard to identify through traditional code analysis; (2) the response to each configuration varies under different flying scenarios. In this article, we propose and implement a novel rectification approach, Nyctea , to detect instability caused by misconfigurations and conduct an on-the-fly rectification. Nyctea first continuously inspects state changes over consecutive time intervals and calculates the overall deviations to determine whether a drone is in a transition of instability to control loss. When a potential instability is reported, Nyctea instantly invokes a pre-trained intelligent agent to automatically generate proper configurations and then re-configure the drone against entering a state of loss of control. This process of reconfiguration is conducted iteratively until the instability is eliminated. We integrated Nyctea with the widely used flight control system, Ardupilot and PX4 . The simulated and practical experiment results showed that Nyctea successfully eliminates instabilities caused by 85% of misconfigurations. For each misconfiguration, Nyctea averagely generated 4 to 5 configurations to achieve a successful rectification.

Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) in the realm of computer vision, showcasing tremendous potential. However, recent research has un-veiled a susceptibility of ViTs to adversarial attacks, akin to their CNN counterparts. Adversarial training and randomization are two representative effective defenses for CNNs. Some researchers have attempted to apply adversarial training to ViTs and achieved comparable robustness to CNNs, while it is not easy to directly apply randomization to ViTs because of the architecture difference between CNNs and ViTs. In this paper, we delve into the structural intricacies of ViTs and propose a novel defense mechanism termed Random entangled image Transformer (ReiT), which seamlessly integrates adversarial training and randomization to bolster the adversarial robustness of ViTs. Recognizing the challenge posed by the structural disparities between ViTs and CNNs, we introduce a novel module, input-independent random entangled self-attention (II-ReSA). This module op-timizes random entangled tokens that lead to “dissimilar” self-attention outputs by leveraging model parameters and the sampled random tokens, thereby synthesizing the self-attention module outputs and random entangled tokens to diminish adversarial similarity. ReiT incorporates two distinct random entangled tokens and employs dual randomization, offering an effective countermeasure against adversarial examples while ensuring comprehensive deduction guarantees. Through extensive experiments conducted on various ViT variants and benchmarks, we substantiate the superiority of our proposed method in enhancing the adversarial robustness of Vision Transformers.

Network dismantling is a process of identifying influential nodes that can decompose a network into disconnected sub-networks. This provides a novel approach to understanding and analyzing complex networks abstracted from the real world. State-of-the-art solutions for this task exploit graph encoders to capture the structural features of the network, which are then sent to the multi-layer perceptron for predicting the node importance. This process, however, fails to exploit the interactions among the graph representations learned from different views and neglects the neighboring information when evaluating node importance. In this work, we address these issues with a graph contrastive learning framework with multi-hop aggregation, resulting in the identification of influential nodes. Firstly, we construct role graphs to provide a holistic view of the original graphs. Secondly, graph representations are obtained in the individual views, and enhanced expressiveness is achieved through contrastive learning. Finally, based on the representations, the multi-hop neighbor information of the nodes is aggregated to rank the node importance, and thus aid in the identification of important nodes. We evaluate our proposal on real and synthetic networks, and the results show that our method outperforms the baseline with fewer nodes required to disassemble a network.

The rapid development of device-edge-cloud collaborative computing techniques has actively contributed to the popularization and application of intelligent service models. The intensity of knowledge transfer plays a vital role in enhancing the performance of intelligent services. However, the existing knowledge transfer methods are mainly implemented through data fine-tuning and model distillation, which may cause the leakage of data privacy or model copyright in intelligent collaborative systems. To address this issue, we propose a secure and robust knowledge transfer framework through stratified-causality distribution adjustment (SCDA) for device-edge-cloud collaborative services. Specifically, a simple yet effective density-based estimation is first employed to obtain uncertainty scores that guide the space stratification, which is conducive to reconstructing low-density distribution regions from high-density distribution regions more adaptively and accurately. Subsequently, we devise a novel causality-aware generative model to generate synthetic features for the out-of-distribution domain by exploring the relationship between factors and variables. Ultimately, we introduce a cycle-consistent minimax optimization mechanism to ensure the effectiveness and dependability of knowledge transfer through the influence minimization and the diversity maximization. Furthermore, extensive experiments demonstrate that our scheme can protect the security of data privacy and model copyright in intelligent collaborative services through adaptive distribution adjustment.

Modern smart TVs often communicate with their remote controls (including the smartphone simulated ones) using multiple wireless channels (e.g., Infrared, Bluetooth, and Wi-Fi). However, this multi-channel remote control communication introduces a new attack surface. An inherent security flaw is that remote controls of most smart TVs are designed to work in a benign environment rather than an adversarial one, and thus wireless communications between a smart TV and its remote controls are not strongly protected. Attackers can leverage such a flaw to abuse the remote control communication and compromise smart TV systems. In this paper, we propose EVILSCREEN, a novel attack that exploits ill-protected remote control communications to access protected resources of a smart TV or even control the screen. EVILSCREEN exploits a multi-channel remote control mimicry vulnerability present in today smart TVs. Unlike other attacks, which compromise the TV system by exploiting code vulnerabilities or malicious third-party apps, EVILSCREEN directly reuses commands of different remote controls, combines them together to circumvent deployed authentication and isolation policies, and finally accesses or controls TV resources remotely. We evaluated eight mainstream smart TVs and found that they are all vulnerable to EVILSCREEN attacks, including a Samsung product adopting the ISO/IEC security specification.

Federated Learning (FL) is an emerging distributed machine learning paradigm crucial for ensuring privacy-preserving learning. In FL, a fair incentive mechanism is indispensable for inspiring more clients to participate in FL training. Nevertheless, achieving a fair incentive mechanism in FL is an arduous endeavor, underscored by two significant challenges that persistently elude resolution within existing methodologies. Firstly, existing works overlook the issue of category distribution heterogeneity in contribution evaluation, leading to incomplete contribution evaluations. Secondly, the fact that malicious servers will dishonestly allocate rewards to save costs is not considered in existing work, which can be a barrier to client participation in FL. This paper introduces FDFL (Fair andDiscrepancy-aware incentive mechanism forFederatedLearning), a novel system addressing these concerns. FDFL encompasses two key elements: 1) Discrepancy-aware contribution evaluation approach; 2) Provable reward allocation approach. Extensive experiments on four model-dataset combinations demonstrate that, under the heterogeneous setting, our scheme improves accuracy by an average of 9.85% and 11.97% compared to FedAvg and FAIR, respectively.

Authentication and cryptography are critical security functions and, thus, are very often included as part of code. These functions require using credentials, such as passwords, security tokens, and cryptographic keys. However, developers often incorrectly implement/use credentials in their code because of a lack of secure coding skills. This paper analyzes open-source projects concerning the correct use of security credentials. We developed a semantic-rich, language-independent analysis approach for analyzing many projects automatically. We implemented a detection tool, SEAGULL, to automatically check open-source projects based on string literal and code structure information. Instead of analyzing the entire project code, which might result in path explosion when constructing data and control dependencies, SEAGULL pinpoints all literal constants to identify credential candidates and then analyzes the code snippets correlated to these candidates. SEAGULL accurately identifies the leaked credentials by obtaining semantic and syntax information about the code. We applied SEAGULL to 377 open-source projects. SEAGULL successfully reported 19 real-world credential leakages out of those projects. Our analysis shows that some developers protected or erased the credentials in the current project versions, but previously used credentials can still be extracted from the project’s historical versions. Although the implementations of credential leakages seem to be fixed in the current projects, attackers could successfully log into accounts if developers keep using the same credentials as before. Additionally, we found that such credential leakages still affect some projects. By exploiting leaked credentials, attackers can log into particular accounts.

The graph neural networks (GNNs) are susceptible to adversarial perturbations and distribution biases, which pose potential security concerns for real-world applications. Current endeavors mainly focus on graph matching, while the subtle relationships between the nodes and structures of graph-structured data remain under-explored. Accordingly, two fundamental challenges arise as follows: 1) the intricate connections among nodes may induce the distribution shift of graph samples even under the same scenario, and 2) the perturbations of inherent graph-structured representations can introduce spurious shortcuts, which lead to GNN models relying on biased data to make unstable predictions. To address these problems, we propose a novel causality-aligned structure rationalization (CASR) scheme to construct invariant rationales by probing the coherent and causal patterns, which facilitates GNN models to make stable and reliable predictions in case of adversarial biased perturbations. Specifically, the initial graph samples across domains are leveraged to boost the diversity of datasets and perceive the interaction between shortcuts. Subsequently, the causal invariant rationales can be obtained during the interventions. This allows the GNN model to extrapolate risk variations from a single observed environment to multiple unknown environments. Moreover, the query feedback mechanism can progressively promote the consistency-driven optimal rationalization by reinforcing real essences and eliminating spurious shortcuts. Extensive experiments demonstrate the effectiveness of our scheme against adversarial biased perturbations from data manipulation attacks and out-of-distribution (OOD) shifts on various graph-structured datasets. Notably, we reveal that the capture of distinctive rationales can greatly reduce the dependence on shortcut cues and improve the robustness of OOD generalization.

When enjoying mobile crowdsensing (MCS), it is vital to evaluate the trustworthiness of mobile users (MUs) without disclosing their sensitive information. However, the existing schemes ignore this requirement in the multiple crowdsourcers (CSs) scenario. The lack of a credible sharing about MUs’ trustworthiness results in an inaccurate trust evaluation, disabling allocating tasks to reliable MUs. To address it, based on the analysis of the desired properties, we propose a scheme enablingdependabledata collection withmultiple crowdsourcerstrustsharing ($D^{2}MTS$). Specifically, we design the MU anonymous management. Two kinds of MU generated pseudonym systems without relationships are presented to mark each MU in trust evaluation and task execution, respectively. Through the devised pseudonym changes on these pseudonyms and the common token distribution algorithm,$D^{2}MTS$realizes privacy-preserving trust sharing. Moreover, to guarantee credible sharing, based on the hash chain,$D^{2}MTS$records MUs’ trustworthiness with the unforgeable signature on the blockchain established by multiple CSs which do not trust each other naturally. Extensive experiments show that compared with the other works,$D^{2}MTS$'s detection ratio of vicious MUs and the percentage of reliable MUs among the selected ones can increase by 208.61% and 28.27%. Both computational and communication delays are limited.

To motivate users' assistance for protecting others' location privacy by distributedK-anonymity in Location-Based Service (LBS), many incentive mechanisms have been proposed, where users obtain monetary compensation for their assistance. However, most existing distributedK-anonymity incentive mechanisms rely on trusted third parties and ignore users' malicious strategies, which destroys LBS's distributed structure as well as leads to users' privacy leakage and incentive ineffectiveness. To solve the above problems, we propose aPrivacy-Enhanced incentive mechAnism for distributedK-anonymity (PEAK). With determining the monetary transaction relationship and location transmission between users, PEAK enables the anonymous cloaking region construction without the trusted server. Meanwhile, PEAK devises role identification mechanism and accountability mechanism to restrain and punish malicious users, which protects users' location privacy and implements effective motivation on users' assistance. Theoretical analysis based on the game theory shows that PEAK constrains users' malicious strategies while satisfying individual rationality, computational efficiency, and satisfaction ratio. Extensive experiments based on the real-world dataset demonstrate that PEAK improves security and feasibility, especially reaching the success rate of anonymous cloaking region construction to more than 90$\%$and decreasing the malicious users' utilities significantly.

Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking various face accessories into consideration, like glasses, hats, and masks. In the COVID-19 pandemic era, wearing face masks is one of the most effective ways to defend against the novel coronavirus. However, DNNs are known to be vulnerable to adversarial examples with a small but elaborated perturbation. Thus, a facial mask with adversarial perturbations may pose a great threat to the widely used deep learning-based FR models. In this paper, we consider a challenging adversarial setting: targeted attack against FR models. We propose a new stealthy physical masked FR attack via adversarial style optimization. Specifically, we train an adversarial style mask generator that hides adversarial perturbations inside style masks. Moreover, to ameliorate the phenomenon of sub-optimization with one fixed style, we propose to discover the optimal style given a target through style optimization in a continuous relaxation manner. We simultaneously optimize the generator and the style selection for generating strong and stealthy adversarial style masks. We evaluated the effectiveness and transferability of our proposed method via extensive white-box and black-box digital experiments. Furthermore, we also conducted physical attack experiments against local FR models and online platforms.

Forgery of facial images and videos has increased the concern about digital security. It has led to the significant development of detecting forgery data recently. However, the data, especially the videos published on the Internet, are usually compressed with lossy compression algorithms such as H.264. The compressed data could significantly degrade the performance of recent detection algorithms. The existing anti-compression algorithms focus on enhancing the performance in detecting heavily compressed data but less consider the compression adaption to the data from various compression levels. We believe creating a forgery detection capable of handling data compressed with unknown levels is important. To enhance the performance of such models, we consider the weak compressed and strong compressed data as two views of the original data and they should have similar representation and relationships with other samples. We propose a novel anti-compression forgery detection framework by maintaining closer relations within data under different compression levels. Specifically, our algorithm measures the pair-wise similarity within data as the relations, ensuring that relationships between weakly and strongly compressed data remain consistent. This enhances the discriminative power for detecting highly compressed data. To achieve a better strong compressed data relation guided by the less compressed one, we apply video-level contrastive learning for weak compressed data, which forces the model to produce similar representations within the same video and far from the negative samples. The experiment results show that the proposed algorithm could boost performance for strong compressed data while improving the accuracy rate when detecting clean data.

To motivate users to submit high quality data for mobile crowdsensing (MCS), some quality-aware incentive mechanisms have been proposed, which recruit and pay users strategically. However, in the existing mechanisms, the recruitment based only on tasks matching degree leads to the ineffective insistent data quality incentive. Meanwhile, the absence of the reasonable payment strategy cannot motivate users to submit high quality data in the current task. To address the above problems, we propose anOnlineall-phase quality-awareincentive mechanism (Oasis) to realize the quality incentive in both recruitment and payment phases. With the knapsack secretary, Oasis first devises a quality-aware pre-budgeting recruitment strategy, which decides whether the arriving user's long-term data quality and bid satisfy the recruited criterion. Then, in the payment phase, Oasis evaluates and updates the current and long-term data qualities of users. Based on the evaluation results, a two-level payment strategy is devised employing the Myerson theorem, where users submitting higher quality data can obtain more utilities under the budget constraint. Theoretical analysis proves that Oasis satisfies economic feasibility and constant competitiveness while achieving quality incentive in recruitment and payment phases. Extensive experiments using the real-world dataset demonstrate that the sensing result accuracy of Oasis increases 67% compared with the existing works.

Developers and manufacturers provide configurable control parameters for flight control programs to support various environments and missions, along with suggested ranges for these parameters to ensure flight safety. However, this flexible mechanism can also introduce a vulnerability known as range specification bugs. The vulnerability originates from the evidence that certain combinations of parameter values may affect the drone's physical stability even though its parameters are within the suggested range. The paper introduces a novel system calledicsearcher, designed to identify incorrect configurations or unreasonable combinations of parameters and suggest more reasonable ranges for these parameters.icsearcherapplies a metaheuristic search algorithm to find configurations with a high probability of driving the drone into unstable states. In particular,icsearcheradopts a machine learning-based predictor to assist the searcher in evaluating the fitness of configuration. Finally, leveraging searched incorrect configurations,icsearchercan summarize the feasible ranges through multi-objective optimization.icsearcherapplies a predictor to guide the search, which eliminates the need for realistic/simulation executions when evaluating configurations and further promotes search efficiency. We have carried out experimental evaluations oficsearcherin different control programs. The evaluation results show that the system successfully reports potentially incorrect configurations, of which over$94\%$leads to unstable states.

Concurrency bugs are one of the most harmful and hard-to-address issues in multithreaded software. Such bugs are hard to discover, reproduce, diagnose or fix due to their non-deterministic nature. Although more and more bug discovery solutions are proposed in recent years, it is difficult to evaluate them with existing concurrency bug datasets. The demand for building a high-quality benchmark of concurrency bugs emerges.

Privacy-preserving image generation has been important for segments such as medical domains that have sensitive and limited data. The benefits of guaranteed privacy come at the costs of generated images' quality and utility due to the privacy budget constraints. The utility is currently measured by the gen2real accuracy (g2r%), i.e., the accuracy on real data of a downstream classifier trained using generated data. However, apart from this standard utility, we identify the “reversed utility” as another crucial aspect, which computes the accuracy on generated data of a classifier trained using real data, dubbed as real2gen accuracy (r2g%). Jointly considering these two views of utility, the standard and the reversed, could help the generation model better improve transferability between fake and real data. Therefore, we propose a novel private image generation method that incorporates a dual-purpose auxiliary classifier, which alternates between learning from real data and fake data, into the training of differentially private GANs. Additionally, our deliberate training strategies such as sequential training contributes to accelerating the generator's convergence and further boosting the performance upon exhausting the privacy budget. Our results achieve new state-of-the-arts over all metrics on three benchmarks: MNIST, Fashion-MNIST, and CelebA.

Abstract The misunderstanding and incorrect configurations of cryptographic primitives have exposed severe security vulnerabilities to attackers. Due to the pervasiveness and diversity of cryptographic misuses, a comprehensive and accurate understanding of how cryptographic misuses can undermine the security of an Android app is critical to the subsequent mitigation strategies but also challenging. Although various approaches have been proposed to detect cryptographic misuse in Android apps, studies have yet to focus on estimating the security risks of cryptographic misuse. To address this problem, the authors present an extensible framework for deciding the threat level of cryptographic misuse in Android apps. Firstly, the authors propose a general and unified specification for representing cryptographic misuses to make our framework extensible and develop adapters to unify the detection results of the state‐of‐the‐art cryptographic misuse detectors, resulting in an adapter‐based detection tool chain for a more comprehensive list of cryptographic misuses. Secondly, the authors employ a misuse‐originating data‐flow analysis to connect each cryptographic misuse to a set of data‐flow sinks in an app, based on which the authors propose a quantitative data‐flow‐driven metric for assessing the overall risk of the app introduced by cryptographic misuses. To make the per‐app assessment more useful for app vetting at the app‐store level, the authors apply unsupervised learning to predict and classify the top risky threats to guide more efficient subsequent mitigation. In the experiments on an instantiated implementation of the framework, the authors evaluate the accuracy of our detection and the effect of data‐flow‐driven risk assessment of our framework. Our empirical study on over 40,000 apps, and the analysis of popular apps reveal important security observations on the real threats of cryptographic misuse in Android apps.

The impact of fog-assisted healthcare Internet of Things (H-IoT) system is immense. The smart H-IoT equipments can upload healthcare information to fog nodes with low latency and high mobility. To facilitate secure interactions among three parties, including smart H-IoT equipments, fog nodes, and a cloud server, over the public and insecure channels, a few authenticated key agreement (AKA) protocols are proposed. However, existing works are constructed based on expensive cryptographic primitives (e.g., bilinear pairing), which lead to high computation costs. Besides, the anonymity of H-IoT users is failed to be provided. To tackle these issues, an anonymous and lightweight three-party AKA protocol (ALAKAP) is proposed, which leverages an efficient cryptographic primitive (i.e., Chebyshev chaotic map operation) to generate a shared session key among three parties and achieve security (anonymity and other six properties) and efficiency simultaneously. It then formally proves the security of ALAKAP under the broadly accepted Burrows–Abadi–Needham (BAN) logic model and demonstrates how the proposed protocol satisfies the desired requirements in the fog-assisted H-IoT system. Finally, the performance of ALAKAP is validated by conducting the experiments on Amazon EC2 and Raspberry Pi. The results show that our work can achieve at least 44% higher improvement than the state-of-the-art works.

Lossless data compression is an effective way to handle the huge transmission and storage overhead of massive text data. Its utility is even more significant today when data volumes are skyrocketing. The concept of operating on compressed data infuses new blood into efficient text management by enabling mainly access-oriented text processing tasks to be done directly on compressed data without decompression. Facing limitations of the existing compressed text processing schemes such as limited types of operations supported, low efficiency, and high space occupation, we address these problems by proposing a homomorphic compression theory. It enables the generalization and characterization of algorithms with compression processing capabilities. On this basis, we develop HOCO, an efficient text data management engine that supports a variety of processing tasks on compressed text. We select three representative compression schemes and implement them combined with homomorphism in HOCO. HOCO supports the extension of homomorphic compression schemes through a modular and object-oriented design and has convenient interfaces for text processing tasks. We evaluate HOCO on six real-world datasets. The three schemes implemented in HOCO show trade-offs in terms of compression ratio, supported operation types, and efficiency. Experiments also show that HOCO can achieve higher throughput in random access and modification operations (averagely 9.18× than the state-of-the-art) and lower latency in text analytic tasks (averagely 7.16× than processing on uncompressed text) without compromising compression efficacy.

The traveling salesman problem (TSP) is one of the classic combinatorial optimization problems, which can be widely used in intelligent transportation and logistics field. Neural network has shown great potential in combinatorial optimization tasks. However, it faces privacy leakage when a TSP neural combinatorial optimization network and user's data are directly outsourced to a cloud platform to provide and request service. In order to address the issue, this article proposes a privacy-preserving service framework for a TSP-based neural combinatorial optimization network called PPSF. We first protect the service provider's model parameters and users’ data by different split methods in multiple cloud servers, providing a secure outsourced mode for the participators in the PPSF framework. Then, in the secure outsourced mode, a series of secure computation protocols are designed for the cloud servers to support performing the secure computing in each service task. Moreover, it can also protect the process that the cloud servers respond to users after data processing and achieve private service result recovery. Finally, we prove that the proposed framework can realize privacy protection for TSP-based combinatorial optimization service and verify its utility and efficiency by experiments.

The existence of native code in Android apps plays an important role in triggering inconspicuous propagation of secrets and circumventing malware detection. However, the state-of-the-art information-flow analysis tools for Android apps all have limited capabilities of analyzing native code. Due to the complexity of binary-level static analysis, most static analyzers choose to build conservative models for a selected portion of native code. Though the recent inter-language analysis improves the capability of tracking information flow in native code, it is still far from attaining similar effectiveness of the state-of-the-art information-flow analyzers that focus on non-native Java methods. To overcome the above constraints, we propose a new analysis framework,$\mu$Dep, to detect sensitive information flows of the Android apps containing native code. In this framework, we combine a control-flow based static binary analysis with a mutation-based dynamic analysis to model the tainting behaviors of native code in the apps. Based on the result of the analyses,$\mu$Dep conducts a stub generation for the related native functions to facilitate the state-of-the-art analyzer DroidSafe with fine-grained tainting behavior summaries of native code. The experimental results show that our framework is competitive on the accuracy, and effective in analyzing the information flows in real-world apps and malware compared with the state-of-the-art inter-language static analysis.

Image steganalysis is a technique to detect whether an image contains hidden information. Although the existing cross-domain steganalysis methods have been presented to narrow the distribution gap between different domains, it is still challenging to effectively capture the transferable steganalysis representations under the condition of severe distribution shifts. To address this issue, we propose a novel consensus-clustering-based automatic distribution matching scheme, called CADM, which can automatically and accurately match inconsistent distributions in cross-domain steganalysis scenarios. First, the original steganalysis features are clustered by the spatially constrained fuzzyc-means (SCFCM) algorithm with controllable parameters to fully perceive and mine inherent structural relationships. Subsequently, the cluster consensus knowledge is derived from the perspective of intra-domain and inter-domain to facilitate the clustering and the matching. In this way, the representations of weak stego signals can be augmented by identifying cluster centers that can be combined across domains. Ultimately, the cycle-consistent optimization and adaptation is achieved by gradually adjusting the learning strength of well-aligned and poorly-aligned samples to promote the positive transfer of overlapped clusters and prevent the negative transfer of outlier clusters. Furthermore, extensive experiments on various benchmark databases for cross-domain steganalysis demonstrate the superiority of CADM over the current state-of-the-art methods.

Location-Based Services (LBSs) are one of the most frequently used mobile applications in the modern society. Geo-Indistinguishability (Geo-Ind) is a promising privacy protection model for LBSs since it can provide formal security guarantees for location privacy. However, Geo-Ind undermines the statistical location distribution of users on the LBS server because of perturbed locations, thereby disabling the server to provide distribution-based services (e.g., traffic congestion maps). To overcome this issue, we give a privacy definition, called DistPreserv, to enable the LBS server to acquire valid location distributions while providing users with strict location protection. Then we propose a privacy-preserving LBS scheme to benefit both users and the server, in which a location perturbation mechanism is designed to achieve the given definition under the guide of the incentive compatibility, and a retrieval area determination method is presented to ensure query accuracy of users by using the dynamic programming on the two-dimensional map plane. Finally, we theoretically prove that the designed mechanism can achieve the definition of DistPreserv and the property of incentive compatibility. Experimental explorations using a real-world dataset indicate that our proposal prominently improves the availability of users’ location distributions by over 90%, while providing high precision and recall of queries.

The tremendous computing capacity of GPU offers significant potential in processing hierarchically compressed text data without decompression. However, current GPU techniques offer only traversal-based text data analytics; random access is exceedingly inefficient, limiting their utility significantly. To address this issue, we develop a novel and widely applicable solution that prompts random access to hierarchically compressed text data without decompression in GPU memory. We address three main challenges for enabling efficient random access to compressed text data on GPUs. The first challenge is designing GPU data structures that facilitate random access. The second challenge is efficiently generating data structures on GPU. The CPU is inefficient when generating data structures for random access, and this inefficiency increases considerably when PCIe transmission is incorporated. The third challenge is query processing on compressed text data in GPU memory. Random accesses, such as data updates, cause massive conflicts among countless threads. In order to address the first challenge, we develop several compressed GPU data structures, including indexing within the intricate GPU memory hierarchy. To handle the second challenge, we propose a two-phase process for producing these data structures on GPU. For the third challenge, a double-parsing design is proposed as a solution to avoid conflicts. We evaluate our solution on three platforms, two server-grade GPU platforms and one edge-grade GPU platform, using five real-world datasets. Experimental results show that random access operations on GPU achieve an average speedup of 52.98× compared to the state-of-the-art solution.

With the popularity of location based services, spatial keyword query has become an important application. In order to save the storage and computational costs, most data owners will outsource the data to the cloud server, but this will lead to two problems, such as privacy leakage and heavy network bandwidth burden. To solve above problems, we propose a Privacy-preserving top-k Spatial Keyword queries based on Fog computing, namly PSKF. To further improve the search efficiency, we use the IR-tree to build the index and store it in the cloud server. Each fog server also saves a different subtree of the IR-tree, so that we can decide which fog server to participate in the query by pruning. Formal security analysis shows that our proposed PSKF achieves Indistinguishability under Known-Plaintext Attacks (IND-KPA), and extensive experiments demonstrate that our proposed scheme is efficient and feasible in practical applications.

Searchable encryption(SE) allows users to efficiently retrieve data over encrypted cloud data, but most existing SE schemes only support exact keyword search, resulting in false results due to minor typos or format inconsistencies of queried keywords. The fuzzy keyword search can avoid this limitation, but still incurs low search accuracy and efficiency. Besides, most of fuzzy keyword search schemes do not consider malicious cloud servers which may execute a fraction of search operations or forge some results due to various interest incentives such as saving computation or storage resources. To solve these problems, we propose an efficient and Verifiable Ranked Fuzzy Multi-keyword Search scheme, called VRFMS. VRFMS uses locality-sensitive hashing and bloom filter to implement fuzzy keyword search, and employs Term Frequency-Inverse Document Frequency(TF-IDF) to sort the relevant results. Aiming to further improve the search accuracy, we design an improved bi-gram keyword transformation method. Furthermore, the homomorphic MAC technique and a random challenge technique are utilized to verify the correctness and completeness of returned results, respectively. Formal security analysis and empirical experiments demonstrate that VRFMS is secure and efficient in practical applications, respectively.

In recent years, with the advances of generative models, many powerful face manipulation systems have been developed based on Deep Neural Networks (DNNs), called DeepFakes. If DeepFakes are not controlled timely and properly, they would become a real threat to both celebrities and ordinary people. Precautions such as adding perturbations to the source inputs will make DeepFake results look distorted from the perspective of human eyes. However, previous method doesn't explore whether the disrupted images can still spoof DeepFake detectors. This is critical for many applications where DeepFake detectors are used to discriminate between DeepFake data and real data due to the huge cost of examining a large amount of data manually. We argue that the detectors do not share a similar perspective as human eyes, which might still be spoofed by the disrupted data. Besides, the existing disruption methods rely on iteration-based perturbation generation algorithms, which is time-consuming. In this paper, we propose a novel DeepFake disruption algorithm called “DeepFake Disrupter”. By training a perturbation generator, we can add the human-imperceptible perturbations to source images that need to be protected without any backpropagation update. The DeepFake results of these protected source inputs would not only look unrealistic by the human eye but also can be distinguished by DeepFake detectors easily. For example, experimental results show that by adding our trained perturbations, fake images generated by StarGAN [5] can result in a 10 ∼ 20% increase in F1-score evaluated by various DeepFake detectors.

Today users can access and/or control their IoT devices using mobile apps. Such interactions often rely on IoT-to-Mobile communication that supports direct data exchanges between IoT devices and smartphones. To guarantee mutual authentication and encrypted data transmission in IoT-to-Mobile communications while keeping lightweight implementation, IoT devices and smartphones often share credentials in advance with the help of a cloud server. Since these credentials impact communication security, in this paper we seek to understand how such sensitive materials are implemented. We design a set of analysis techniques and implement them in KingFisher, an analysis framework. KingFisher identifies shared credentials, tracks their uses, and examines violations against nine security properties that the implementation of credentials should satisfy. With an evaluation of eight real-world IoT solutions with more than 35 million deployed devices, KingFisher revealed that all these solutions involve insecurely used credentials, and are subject to privacy leakage or device hijacking.

In order to support a variety of missions and deal with different flight environments, drone control programs typically provide configurable control parameters. However, such a flexibility introduces vulnerabilities. One such vulnerability, referred to as range specification bugs, has been recently identified. The vulnerability originates from the fact that even though each individual parameter receives a value in the recommended value range, certain combinations of parameter values may affect the drone physical stability. In this paper, we develop a novel learning-guided search system to find such combinations, that we refer to as incorrect configurations. Our system applies metaheuristic search algorithms mutating configurations to detect the configuration parameters that have values driving the drone to unstable physical states. To guide the mutations, our system leverages a machine learning based predictor as the fitness evaluator. Finally, by utilizing multi-objective optimization, our system returns the feasible ranges based on the mutation search results. Because in our system the mutations are guided by a predictor, evaluating the parameter configurations does not require realistic/simulation executions. Therefore, our system supports a comprehensive and yet efficient detection of incorrect configurations. We have carried out an experimental evaluation of our system. The evaluation results show that the system successfully reports potentially incorrect configurations, of which over 85% lead to actual unstable physical states.

Linux drivers share the same address space and privilege with the core of the kernel but have a much larger code base and attack surface. The Linux drivers are not well tested and have weaker security guarantees than the kernel. Missing support from hardware devices, existing fuzzing solutions fail to cover a large portion of the driver code, e.g., the initialization code and interrupt handlers. In this paper, we present PrIntFuzz, an efficient and universal fuzzing framework that can test the overlooked driver code, including the PRobing code and INTerrupt handlers. PrIntFuzz first extracts knowledge from the driver through inter-procedural field-sensitive, path-sensitive, and flow-sensitive static analysis. Then it utilizes the information to build a flexible and efficient simulator, which supports device probing, hardware interrupts emulation and device I/O interception. Lastly, PrIntFuzz applies a multi-dimension fuzzing strategy to explore the overlooked code. We have developed a prototype of PrIntFuzz and successfully simulated 311 virtual PCI (Peripheral Component Interconnect) devices, 472 virtual I2C (Inter-Integrated Circuit) devices, 169 virtual USB (Universal Serial Bus) devices, and found 150 bugs in the corresponding device drivers. We have submitted patches for these bugs to the Linux kernel community, and 59 patches have been merged so far. In a control experiment of Linux 5.10-rc6, PrIntFuzz found 99 bugs, while the state-of-the-art fuzzer only found 50. PrIntFuzz covers 11,968 basic blocks on the latest Linux kernel, while the state-of-the-art fuzzer Syzkaller only covers 2,353 basic blocks.

Protecting confidential data against memory disclosure attacks is crucial to many critical applications, especially those involve cryptographic operations. However, it is neither easy to identify involved cryptographic confidential data in a program nor to implement a fine-grained and yet efficient protection. Existing defensive techniques face many shortcomings such as coarse-grained protection or exorbitant overhead. As a result, real world crypto applications seldom applied this kind of protection in practice.To make the protection of cryptographic confidential data practical, we design and implement CRYPTOMPK, a source code analysis and transformation system to implement a domain-based memory isolation. CRYPTOMPK first automatically tracks and labels all sensitive memory buffers and operations in source code with a context-sensitive, crypto-aware information flow analysis. Then it partitions the source code into crypto and non-crypto domains with a context-dependent privilege switch instrumentation. By further utilizing Intel Memory Protection Keys (MPK), CRYPTOMPK generates executables with efficient domain switching, protecting them against typical memory disclosure vulnerabilities such as arbitrary memory read. In particular, by using CRYPTOMPK, a large number of intermediate memory buffers that have been previously ignored before are well protected, and thus the security risks are reduced significantly. We leveraged CRYPTOMPK to protect prevalent applications such as Apache and Nginx with widely used crypto libraries (e.g., OpenSSL, LibSodium). CRYPTOMPK only needs several minutes to analyze each of these complex cryptographic programs and incurs at most 9.53% performance overhead for the protected programs.

Existing tools for the automated detection of memory corruption bugs are not very effective in practice. They typically recognize only standard memory management (MM) APIs (e.g., malloc and free) and assume a naive paired-use model—an allocator is followed by a specific deallocator. However, we observe that programmers very often design their own MM functions and that these functions often manifest two major characteristics: (1) Custom allocator functions perform multi-object or nested allocation which then requires structure-aware deallocation functions. (2) Custom allocators and deallocators follow an unpaired-use model. A more effective detection thus needs to adapt those characteristics and capture memory bugs related to non-standard MM behaviors. In this paper, we present a MM function aware memory bug detection technique by introducing the concept of structure-aware and object-centric Memory Operation Synopsis (MOS). A MOS abstractly describes the memory objects of a given MM function, how they are managed by the function, and their structural relations. By utilizing MOS, a bug detection could explore much less code but is still capable of handling multi-object or nested allocations and does not rely on the paired-use model. In addition, to extensively find MM functions and automatically generate MOS for them, we propose a new identification approach that combines natural language processing (NLP) and data flow analysis, which enables the efficient and comprehensive identification of MM functions, even in very large code bases. We implement a MOS-enhanced memory bug detection system, Goshawk, to discover memory bugs caused by complex and custom MM behaviors. We applied Goshawk to well-tested and widely-used open source projects including OS kernels, server applications, and IoT SDKs. Goshawk outperforms the state-of-the-art data flow analysis driven bug detection tools by an order of magnitude in analysis speed and the number of accurately identified MM functions, reports the discovered bugs with a developer-friendly, MOS based description, and successfully detects 92 new double-free and use-after-free bugs.

Controller area network (CAN) bus anomaly detection on the Internet of Vehicles (IoV) is a topic of ongoing interest and increasing importance, particularly as IoV becomes commonplace. However, existing abnormal detection schemes are not ideal due to the lack of abnormal data in IoV and the difficulty of parsing the diverse message rules in existing vehicles. While single-classification of the support vector domain description (SVDD) algorithm can detect abnormalities only with normal message information, the approach has a high rate of false negatives when deployed directly in the in-vehicle network environment. In addition, the real-time data generation (e.g., IoV messages) compounds the challenge of designing effective detection approaches. Therefore, this article proposes a mechanism for car networking message classification for a broad range of data, and establishes a weak model for many simple redundant data in the vehicle Intranet. The detection can reduce the time and computation costs of detection while ensuring accuracy. Then, this article proposes two improved SVDD schemes: 1) M-SVDD scheme, which adds the Markov chain to detect time-related messages and 2) G-SVDD scheme, which maps the kernel function to the Gaussian kernel function to reduce the redundant area of the model and the false-negative rate. The experimental results show that our proposed schemes have higher accuracy, recall rate, and fewer computation overhead.

Passwords are pervasively used to authenticate users’ identities in mobile apps. To secure passwords against attacks, protection is applied to the password authentication protocol (PAP). The implementation of the protection scheme becomes an important factor in protecting PAP against attacks. We focus on two basic protection in Android, i.e., SSL/TLS-based PAP and timestamp-based PAP. Previously, we proposed an automated tool,GLACIATE, to detect authentication flaws. We were curious whether orchestration (i.e., involving manual-effort) works better than automation. To answer this question, we propose an orchestrated approach,AuthExploitand compare its effectivenessGLACIATE. We study requirements for correct implementation of PAP and then applyGLACIATEto identify protection enhancements automatically. Through dependency analysis,GLACIATEmatches the implementations against the abstracted flaws to recognise defective apps. To evaluateAuthExploit, we collected 1,200 Android apps from Google Play. We comparedAuthExploitwith the automation tool,GLACIATE, and two other orchestration tools,${\sf MalloDroid}$and${\sf SMV-Hunter}$. The results demonstrated that orchestration tools detect flaws more precisely although the F1 score ofGLACIATEis higher thanAuthExploit. Further analysis of the results reveals that highly popular apps and e-commerce apps are not more secure than other apps.

In this paper, we propose a lightweight privacy-preserving Faster R-CNN framework (SecRCNN) for object detection in medical images. Faster R-CNN is one of the most outstanding deep learning models for object detection. Using SecRCNN, healthcare centers can efficiently complete privacy-preserving computations of Faster R-CNN via the additive secret sharing technique and edge computing. To implement SecRCNN, we design a series of interactive protocols to perform the three stages of Faster R-CNN, namely feature map extraction, region proposal and regression and classification. To improve the efficiency of SecRCNN, we improve the existing secure computation sub-protocols involved in SecRCNN, including division, exponentiation and logarithm. The newly proposed sub-protocols can dramatically reduce the number of messages exchanged during the iterative approximation process based on the coordinate rotation digital computer algorithm. Moreover, the effectiveness, efficiency and security of SecRCNN are demonstrated through comprehensive theoretical analysis and extensive experiments. The experimental findings show that the communication overhead in computing division, logarithm and exponentiation decreases to 36.19%, 73.82% and 43.37%, respectively.

One of the key challenges for the implementation of visual recognition systems in the real world is to construct prediction models that can realize the knowledge transfer from the seen data to the unseen data. Specifically, partial knowledge transfer (PKT) aims to address a more common and realistic scenario in which we are accessible to a label-rich source domain while working on a relative label-scarce target domain. The essence of PKT is to explore the latent categories across different domains and simultaneously facilitate the positive transfer from these data. In this article, we propose a joint loss-aware consistency learning (JLACL) to effectively enhance the transferability of knowledge in visual recognition systems, which conducts an iterative optimization on three-level losses, including discrepancy loss, consensus loss, and cross-entropy loss. The discrepancy loss is designed to eliminate the class distribution bias by a similarity perception metric between the source and target domains. The consensus loss can assist to preserve domain-invariant and representative features for model learning by exploring correlation. Moreover, we also find that using the cross-entropy loss to determine the shared label space, which can help to alleviate the negative transfer by suppressing the features with nonshared labels. Finally, the PKT can be successfully achieved by joint optimization of total losses. Extensive experiments on several public and challenging datasets in visual recognition applications adequately demonstrate the superiority of our proposed JLACL over existing state-of-the-art PKT methods.

The development of Industrial Internet of Things (IIoT) provides massive abundant data resources for trading and mining. However, the existing data trading schemes achieve data usage control at the cost of high latency, thereby resulting in poor service quality as the values of IIoT data degrade over time. This article proposes a monitor-based usage control model to enforce data usage policies on the user side, which eliminates frequent interactions between owners and users. Based on that, a data trading scheme with efficient usage control for IIoT (called DTSI) is devised, which utilizes blockchain smart contract and software guard extensions (SGX) to enable owners to fully control users’ identities and operations at minimal overhead. Security analysis shows that DTSI effectively prevents data abuse and ensures the fair exchange of data. Meanwhile, extensive experiments are conducted on the DTSI prototype comparing with the state-of-the-art schemes with real-world IIoT datasets, which demonstrates the efficiency of DTSI.

Recent IoT applications gradually adapt more complicated end systems with commodity software. Ensuring the runtime integrity of these software is a challenging task for the remote controller or cloud services. Popular enforcement is the runtime remote attestation which requires the end system (prover) to generate evidence for its runtime behavior and a remote trusted verifier to attest the evidence. Control-flow attestation is a kind of runtime attestation that provides diagnoses towards the remote control-flow hijacking at the prover. Most of these attestation approaches focus on small or embedded software. The recent advance to attesting complicated software depends on the source code and CFG traversing to measure the checkpoint-separated subpaths, which may be unavailable for commodity software and cause possible context missing between consecutive subpaths in the measurements.

A fundamental premise of SMS One-Time Password (OTP) is that the used pseudo-random numbers (PRNs) are uniquely unpredictable for each login session. Hence, the process of generating PRNs is the most critical step in the OTP authentication. An improper implementation of the pseudo-random number generator (PRNG) will result in predictable or even static OTP values, making them vulnerable to potential attacks. In this paper, we present a vulnerability study against PRNGs implemented for Android apps. A key challenge is that PRNGs are typically implemented on the server-side, and thus the source code is not accessible. To resolve this issue, we build an analysis tool, OTP-Lint, to assess implementations of the PRNGs in an automated manner without the source code requirement. Through reverse engineering, OTP-Lint identifies the apps using SMS OTP and triggers each app's login functionality to retrieve OTP values. It further assesses the randomness of the OTP values to identify vulnerable PRNGs. By analyzing 6,431 commercially used Android apps downloaded from Google Play and Tencent Myapp, OTP-Lint identified 399 vulnerable apps that generate predictable OTP values. Even worse, 194 vulnerable apps use the OTP authentication alone without any additional security mechanisms, leading to insecure authentication against guessing attacks and replay attacks.

The first international Workshop on Programming Language Processing presents interdisciplinary contributions that address programming language procession problems with machine learning and data mining techniques. Recently, there are lots of successful natural language processing methods. But the mining of programming languages could not exactly follow the manner of natural language processing. The difference between natural language and programming language brings in new research challenges and opportunities. The workshop will bring together researchers from machine learning, data mining and software engineering to discuss and debate the path forward for mining the value of programming languages.

Dynamic taint analysis (DTA) has been widely used in various security-relevant scenarios that need to track the runtime information flow of programs. Dynamic binary instrumentation (DBI) is a prevalent technique in achieving effective dynamic taint tracking on commodity hardware and systems. However, the significant performance overhead incurred by dynamic taint analysis restricts its usage in production systems. Previous efforts on mitigating the performance penalty fall into two categories, parallelizing taint tracking from program execution and abstracting the tainting logic to a higher granularity. Both approaches have only met with limited success. In this work, we propose Sdft, an efficient approach that combines the precision of DBI-based instruction-level taint tracking and the efficiency of function-level abstract taint propagation. First, we build the library function summaries automatically with reachability analysis on the program dependency graph (PDG) to specify the control- and data dependencies between the input parameters, output parameters, and global variables of the target library. Then we derive the taint rules for the target library functions and develop taint tracking for library function that is tightly integrated into the state-of-the-art DTA framework Libdft. By applying our approach to the core C library functions of glibc, we report an average of 1.58x speed up of the tracking performance compared with Libdft64. We also validate the effectiveness of the hybrid taint tracking and the ability on detecting real-world vulnerabilities.

As a new computing paradigm, edge computing has appeared in the public field of vision recently. Owing to its advantages of low delay and fast response, edge computing has become an important assistant of cloud computing and has brought new opportunities for diverse smart applications like the smart grid, the smart home, and the smart transportation. However, the accompanying security issues, which have always been the focus of users' concern, still cannot be ignored. Therefore, we focus on the security issues in this overview. We first introduce some related definitions of edge computing and present the architecture for edge computing-based smart applications. After illustrating the smart applications, from the perspective of identity authentication and data security, we analyze the security protection requirements of these smart applications in the edge computing environment. Next, we review some state-of-the-art works on them. Furthermore, we present the extended discussions on the applicability of these current works in the edge computing environment. Finally, we briefly discuss the future work on authentication and data security of edge computing-based smart applications.

This paper investigates the fundamental covert rate performance in a wireless relaying system consisting of a source-destination pair, a full-duplex (FD) relay and a warden, where the relay can work at either the FD mode or the half-duplex (HD) mode. We first provide theoretical modeling for the instantaneous/average covert rate when the system works solely under the FD mode or HD mode, and then explore the corresponding optimal transmit power control of relay for the covert rate maximization. For an improvement of covert rate, we further propose a joint FD/HD mode that flexibly switches between the FD and HD modes depending on channel state of the relay self-interference channel. Under the joint FD/HD mode, we also examine the related problems of theoretical modeling for covert rate and optimal transmit power control of relay for covert rate maximization. Finally, extensive numerical results are provided to illustrate the covert rate performances of the relaying system under the FD, HD and joint FD/HD modes.

Wi-Fi hotspot-based data clone services are increasingly used by Android users to transfer their user data and preferred configurations while upgrading obsolete phones to new models. Unfortunately, since the data clone services need to manipulate sensitive information protected by the Android system, vulnerabilities in the design or implementation of these services may result in data privacy breaches. In this paper we present an empirical security analysis of eight widely used Wi-Fi hotspot-based data clone services deployed to millions of Android phones. Our study evaluates those services with respect to data export/import, data transmission, and Wi-Fi configuration with respect to security requirements that the data clone procedure should satisfy. Since data clone services are closed source, we design Poirot, an analysis system to recover workflows of the data clone services and detect potential flaws. Our study reveals a series of critical security issues in the data clone services. We demonstrate two types of attacks that exploit the data clone service as a new attack surface. A vulnerable data clone service allows attackers to retrieve sensitive user data without permissions, and even inject malicious contents to compromise the system.

Recently, Google and other 24 institutions proposed a series of open challenges towards federated learning (FL), which include application expansion and homomorphic encryption (HE). The former aims to expand the applicable machine learning models of FL. The latter focuses on who holds the secret key when applying HE to FL. For the naive HE scheme, the server is set to master the secret key. Such a setting causes a serious problem that if the server does not conduct aggregation before decryption, a chance is left for the server to access the user’s update. Inspired by the two challenges, we propose FEDXGB, a federated extreme gradient boosting (XGBoost) scheme supporting forced aggregation. FEDXGB mainly achieves the following two breakthroughs. First, FEDXGB involves a new HE based secure aggregation scheme for FL. By combining the advantages of secret sharing and homomorphic encryption, the algorithm can solve the second challenge mentioned above, and is robust to the user dropout. Then, FEDXGB extends FL to a new machine learning model by applying the secure aggregation scheme to the classification and regression tree building of XGBoost. Moreover, we conduct a comprehensive theoretical analysis and extensive experiments to evaluate the security, effectiveness, and efficiency of FEDXGB. The results indicate that FEDXGB achieves less than 1% accuracy loss compared with the original XGBoost, and can provide about 23.9% runtime and 33.3% communication reduction for HE based model update aggregation of FL.

Cloud-based Convolutional neural network (CNN) is a powerful tool for the healthcare center to provide health condition monitor service. Although the new service has future prospects in the medical, patient's privacy concerns arise because of the sensitivity of medical data. Prior works to address the concern have the following unresolved problems: 1) focus on data privacy but neglect to protect the privacy of the machine learning model itself; 2) introduce considerable communication costs for the CNN inference, which lowers the service quality of the cloud server. To push forward this area, we propose PE-HEALTH, a privacy-preserving health monitor framework that supports fully-encrypted CNN (both input data and model). In PE-HEALTH, the medical Internet of Things (IoT) sensor serves as the health condition data collector. For protecting patient privacy, the IoT sensor additively shares the collected data and uploads the shared data to the cloud server, which is efficient and suited to the energy-limited IoT sensor. To keep model privacy, PE-HEALTH allows the healthcare center to previously deploy, and then, use an encrypted CNN on the cloud server. During the CNN inference process, PE-HEALTH does not need the cloud servers to exchange any extra messages for operating the convolutional operation, which can greatly reduce the communication cost.

The immutable feature of blockchain determines that traditional security response mechanisms (e.g., code patching) must change to remedy insecure smart contracts. The only proper way to protect a smart contract is to fix potential risks in its code before it is deployed to the blockchain. However, existing tools for smart contract security analysis focus on the detection of bugs but seldom consider the code fix issues. Meanwhile, it is often time-consuming and error-prone for a developer to understand and fix flawed code manually. In this paper we propose SMARTSHIELD, a bytecode rectification system, to fix three typical security-related bugs (i.e., state changes after external calls, missing checks for out-of-bound arithmetic operations, and missing checks for failing external calls) in smart contracts automatically and help developers release secure contracts. Moreover, SMARTSHIELD guarantees that the rectified contract is not only immune to certain attacks but also gas-friendly (i.e., a slightly increase of gas cost). To evaluate the effectiveness and efficiency of SMARTSHIELD, we applied it to 28,621 real-world buggy contracts on Ethereum blockchain (as of January 2nd2019). Experiment results demonstrated that among 95,502 insecure cases in those contracts, 87,346 (91.5%) of them were automatically fixed by SMARTSHIELD. A following test with both program analysis and real-world exploits further testified that the rectified contracts were secure against common attacks. Moreover, the rectification only introduced a 0.2 % gas increment for each contract on average.

Smart contracts, programs running on blockchain systems, leverage diverse decentralized applications (DApps). Unfortunately, well-known smart contract platforms, Ethereum for example, face serious security problems. Exploits to contracts may cause enormous financial losses, which emphasize the importance of smart contract testing. However, current exploit generation tools have difficulty to solve hard constraints in execution paths and cannot simulate the blockchain behaviors very well. These problems cause a loss of coverage and accuracy of exploit generation. To overcome the problems, we design and implement EthPloit, a smart contract exploit generator based on fuzzing. EthPloit adopts static taint analysis to generate exploit-targeted transaction sequences, a dynamic seed strategy to pass hard constraints and an instrumented Ethereum Virtual Machine to simulate blockchain behaviors. We evaluate EthPloit on 45,308 smart contracts and discovered 554 exploitable contracts. EthPloit automatically generated 644 exploits without any false positive and 306 of them cannot be generated by previous exploit generation tools.

Nowadays, the pseudonym swap has become the mainstream technology for protecting vehicles' trajectory privacy in vehicle ad hoc networks. However, the existing pseudonym swap methods cannot strictly provide the unlinkability between the new pseudonym and old pseudonym of the vehicle due to the lack of theoretical privacy guarantee, resulting in severe leakages of vehicles' trajectory privacy. Our experiment also proves this point and we find that existing works may cause vehicle's pseudonyms to be linked with a probability higher than 60% because they always choose two vehicles with very different driving states (e.g., speeds, directions, and positions) to swap their pseudonyms. To solve this issue, we first give a formal privacy definition based on generalized differential privacy, called pseudonym indistinguishability, to provide a strict unlinkability for pseudonym swap. Then, we design an appropriate utility metric and a new pseudonym swap mechanism, which selects a pseudonym for a vehicle by adapting a differential privacy exponential mechanism to satisfy pseudonym indistinguishability. Abstracting from attackers' prior knowledge, we can strictly guarantee that if two vehicles have a high similarity of driving states, it is impossible for attackers to link the vehicles and their pseudonyms after the swap. Theoretical analyses prove that our mechanism satisfies the proposed privacy definition, thus ensuring the unlinkability between the new pseudonym and the old pseudonym. Extensive experiments on a real data set show that our work only requires about 50% of pseudonym quantities compared to other works and can make the vehicle successfully complete the swap process with a probability of more than 90%, which is higher than any of existing works.

With the development of Industry 4.0, the communication of smart grid has recently been taken seriously to ensure secure communication between operator and control center. However, the authentication process between them faces many challenges. Once the attacker successfully authenticated in the control center, the privacy data in the smart grid may leak and cause irreparable damage to the user. In addition, operator authentication is one of the most basic and crucial processes. Therefore, we propose theeye-movement and iris recognition based authentication (EmIr-Auth), a novel biometrics-based remote operator authentication scheme.EmIr-Authuses the recorded eye-movement trajectory and randomly selected iris image to authenticate operators, which is beneficial in that it is able to get rid of many cryptographic computations, as well as the need to minimize message exchange. Furthermore, except for a high-resolution camera, we do not require any additional biometric sensors in this scheme. Using the Burrows–Abadi–Needham logic, in this article, we demonstrate that our scheme provides secure authentication. Moreover, we analyze the attacks thatEmIr-Authcan resist by informal security analysis. Experimental results show thatEmIr-Authis efficient enough to deploy on portable devices and reduce the overhead of authentication procedure.

A great quantity of user passwords nowadays has been leaked through security breaches of user accounts. To enhance the security of the Password Authentication Protocol (PAP) in such circumstance, Android app developers often implement a complementary One-Time Password (OTP) authentication by utilizing the short message service (SMS). Unfortunately, SMS is not specially designed as a secure service and thus an SMS One-Time Password is vulnerable to many attacks. To check whether a wide variety of currently used SMS OTP authentication protocols in Android apps are properly implemented, this paper presents an empirical study against them. We first derive a set of rules from RFC documents as the guide to implement secure SMS OTP authentication protocol. Then we implement an automated analysis system, AUTH-EYE, to check whether a real-world OTP authentication scheme violates any of these rules. Without accessing server source code, AUTH-EYE executes Android apps to trigger the OTP-relevant functionalities and then analyzes the OTP implementations including those proprietary ones. By only analyzing SMS responses, AUTH-EYE is able to assess the conformance of those implementations to our recommended rules and identify the potentially insecure apps. In our empirical study, AUTH-EYE analyzed 3,303 popular Android apps and found that 544 of them adopt SMS OTP authentication. The further analysis of AUTH-EYE demonstrated a far-from-optimistic status: the implementations of 536 (98.5%) out of the 544 apps violate at least one of our defined rules. The results indicate that Android app developers should seriously consider our discussed security rules and violations so as to implement SMS OTP properly.

Before the final attack happens, clandestine attackers conduct sequenced stages for being stealthy and elusive. These attacks can leave clues in several different log files. Howeverexisting approaches can only detect the anomalies using single type of log and fail to reveal all of the attack steps through log integration and correlation. Such methods can hardly detect the relationships among events and prevent the attack in advance. Additionally, traditional machine learning or data mining in log analysis has a high overhead in computing which is impractically applied in a real product or system. To address these problems, we present AClog, a multiple log correlated analysis system to construct the attack chain. Inspired by penetration testing and social network analysis, we transfer the attack provenance as an event relationship discover problem. We use different logs to form the steps of the system and regard them as the event sequences before the attack. Then, we leverage Fast Linear SVM and Longest Common Subsequences to find out the regular steps before the attack. Finally, we spot the corresponding log sequences to identify the pre- attackk steps proactively. We apply our approach in the attack prediction of a cloud computing platform and a university network. The results show that the proposed method can effectively and precisely construct the attack steps and identify the corresponding syslogs.

Cryptography is increasingly being used in mobile applications to provide various security services; from user authentication, data privacy, to secure communications. However, there are plenty of mistakes that developers could accidentally make when using cryptography in their mobile apps and such mistakes can lead to a false sense of security. Recent research efforts indeed show that a significant portion of mobile apps in both Android and iOS platforms misused cryptographic APIs. In this paper, we present CDRep, a tool for automatically repairing cryptographic misuse defects in Android apps. We classify such defects into seven types and manually assemble the corresponding fix patterns based on the best practices in cryptographic implementations. CDRep consists of two phases, a detection phase which identifies defect locations in a mobile app and a repair phase which repairs the vulnerable app automatically. In our validation, CDRep is able to successfully repair 94.5% of 1,262 vulnerable apps. Furthermore, CDRep is lightweight, the average runtime to generate a patch is merely 19.3 seconds and the size of a repaired app increases by only 0.667% on average.

Mobile applications are popular in recent years. They are often allowed to access and modify users' sensitive data. However, many mobile applications are malwares that inappropriately use these sensitive data. To detect these malwares, Gorla et al. Propose CHABADA which compares app behaviors against its descriptions. Data about known malwares are not used in their work, which limits its effectiveness. In this work, we extend the work by Gorla et al. By proposing an active and semi-supervised approach for detecting malwares. Different from CHABADA, our approach will make use of both known benign and malicious apps to predict other malicious apps. Also, our approach will select a good set of apps for experts to label as malicious or benign to form a set of labeled training data -- it is an active approach. Furthermore, it will make use of both labeled data (known malicious or benign apps) and unlabeled data (unknown apps) -- it is a semi-supervised approach. We have evaluated our approach by using a set of 22,555 Android apps. Our approach achieves a good performance in detecting malicious apps with a precision of 99.82%, recall of 92.50%, and F-measure of 96.02%. Our approach improves CHABADA by 365.8%, 64.8%, 209.6% in terms of precision, recall, and F-measure.

Attribute-based encryption (ABE) with outsourced decryption not only enables fine-grained sharing of encrypted data, but also overcomes the efficiency drawback (in terms of ciphertext size and decryption cost) of the standard ABE schemes. In particular, an ABE scheme with outsourced decryption allows a third party (e.g., a cloud server) to transform an ABE ciphertext into a (short) El Gamal-type ciphertext using a public transformation key provided by a user so that the latter can be decrypted much more efficiently than the former by the user. However, a shortcoming of the original outsourced ABE scheme is that the correctness of the cloud server's transformation cannot be verified by the user. That is, an end user could be cheated into accepting a wrong or maliciously transformed output. In this paper, we first formalize a security model of ABE with verifiable outsourced decryption by introducing a verification key in the output of the encryption algorithm. Then, we present an approach to convert any ABE scheme with outsourced decryption into an ABE scheme with verifiable outsourced decryption. The new approach is simple, general, and almost optimal. Compared with the original outsourced ABE, our verifiable outsourced ABE neither increases the user's and the cloud server's computation costs except some nondominant operations (e.g., hash computations), nor expands the ciphertext size except adding a hash value (which is <;20 byte for 80-bit security level). We show a concrete construction based on Green et al.'s ciphertext-policy ABE scheme with outsourced decryption, and provide a detailed performance evaluation to demonstrate the advantages of our approach.