The explosive growth and increasing complexity of modern 5G/6G networks, driven by Internet-of-Things (IoT), industrial automation, and real‑time multimedia streaming, demand forecasting methods that address non‑stationarity, abrupt shifts, and incomplete observations. Non‑stationarity involves changing statistical properties, abrupt shifts stem from events or outages, and data gaps can impair model accuracy. Traditional statistical models and deep sequence learners partially handle these challenges but often leave systematic residuals, which are structured errors from unmodeled scenarios and overlook high‑level contextual cues such as external events or semantic patterns. To overcome these limitations, we propose a hybrid forecasting framework combining a convolutional neural network–long short-term memory (CNN–LSTM) trend predictor for capturing local fluctuations and long‑range dependencies, an Extreme Gradient Boosting (XGBoost) residual corrector to refine forecast errors, and a Low-Rank Adaptation (LoRA)‑fine‑tuned large language model (LLM) that generates semantic labels of trend direction, anomaly type, and volatility regime to enrich residual learning. Experimental evaluation on real‑world cellular traffic data shows up to 15% reduction in root-mean-square error (RMSE) and 10% reduction in mean absolute percentage error (MAPE) compared to state‑of‑the‑art hybrid baselines, with substantially improved resilience to noise, missing data, and abrupt traffic surges. Our contributions include a parameter‑efficient prompt‑based LoRA fine‑tuning pipeline for adapting LLMs to time‑series forecasting, a context‑aware residual learning architecture fusing numerical and linguistic features, and comprehensive empirical validation demonstrating superior accuracy and robustness in dynamic network environments.

Money laundering is a financial crime that obscures the origin of illicit funds, necessitating the development and enforcement of anti-money laundering (AML) policies by governments and organizations. The proliferation of mobile payment platforms and smart IoT devices has significantly complicated AML investigations. As payment networks become more interconnected, there is an increasing need for efficient real-time detection to process large volumes of transaction data on heterogeneous payment systems by different operators such as digital currencies, cryptocurrencies and account-based payments. Most of these mobile payment networks are supported by connected devices, many of which are considered loT devices in the FinTech space that constantly generate data. Furthermore, the growing complexity and unpredictability of transaction patterns across these networks contribute to a higher incidence of false positives. While machine learning solutions have the potential to enhance detection efficiency, their application in AML faces unique challenges, such as addressing privacy concerns tied to sensitive financial data and managing the real-world constraint of limited data availability due to data regulations. Existing surveys in the AML literature broadly review machine learning approaches for money laundering detection, but they often lack an in-depth exploration of advanced deep learning techniques—an emerging field with significant potential. To address this gap, this paper conducts a comprehensive review of deep learning solutions and the challenges associated with their use in AML. Additionally, we propose a novel framework that applies the least-privilege principle by integrating machine learning techniques, codifying AML red flags, and employing account profiling to provide context for predictions and enable effective fraud detection under limited data availability. Specifically, our approach defines AML-relevant financial profile characteristics and risk indicators to contextualize transactions and assess their associated risks. The proposed context-risk-predict AML (CRP-AML) model demonstrates notable success, achieving an F1 score of 82.51% on the minority class and nearly doubling the performance of other pattern detection models when the proportion of money laundering records in the dataset drops as low as 0.0005.

The widespread use of AI-generated text has introduced significant security concerns, driving the need for reliable detection systems. However, recent studies reveal that neural network-based detectors are vulnerable to adversarial examples. To improve the robustness of such classifiers, a number of adversarial attack strategies have been developed, particularly in the context of text sentiment classification. Most existing adversarial attack methods focus on the semantics of individual words or sentences, often neglecting the broader contextual semantics of the entire text-particularly in the case of long AI-generated text. This limitation frequently results in adversarial examples that lack fluency and coherence. In this paper, we propose a novel method calledSentence-based Adversarial attack on AI-Generated Text detectors (SAGT), which generates linguistically fluent adversarial examples by inserting model-generated sentences into the original text. To ensure contextual semantic consistency, we extract important keywords from the original text-selected based on changes in the detector's confidence score-and incorporate them into the generated sentences. Extensive experimental results demonstrate that adversarial examples crafted bySAGTcan effectively evade AI-generated text detectors.

Federated Learning (FL) has emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct data sharing. However, recent studies show that attackers can steal private data through model manipulation or gradient analysis. Existing attacks are constrained by low theft quantity or low-resolution data, and they are often easily detected through anomaly monitoring in gradients or weights. In this paper, we propose Sleight, a novel data-reconstruction attack, supported by two key techniques, i.e., distinctive and sparse encoding design and block partitioning. Unlike conventional methods that require detectable changes to the model, Sleight stealthily embeds a hidden model using parameter sharing to systematically extract sensitive data. The Fibonacci-based index design ensures efficient, structured retrieval of memorized data, while the block partitioning method enhances Sleight's capability to handle high-resolution images by dividing them into smaller, manageable units. Extensive experiments on 4 datasets confirmed that Sleight is superior to 5 state-of-the-art data-reconstruction attacks under 5 respective detection methods. Sleight can handle large-scale and high-resolution data without being detected or mitigated by state-of-the-art data reconstruction defense methods. In contrast to baselines, Sleight can be directly applied to both FedAvg and FedSGD scenarios, underscoring the need for developers to devise new defenses against such vulnerabilities. We will open-source our code upon acceptance.

The pervasive spread of fake news, particularly through manipulated images, presents a consequential negative impact on society. To prevent fake news images from misleading the public, existing methods focus on verifying the authenticity of news images but ignore source traceability, leaving a gap in creating a complete forensic chain for reliable fake news detection. To simultaneously achieve the goals of authenticity verification and source tracing, we propose a proactive image tagging approach based on a design of Disentangled Invertible Neural Networks (DINN). It can simultaneously embed the dual-tags,i.e., authenticable tag and traceable tag, into each news image prior to publication, allowing for separate extraction for authenticity verification and source tracing. Within the proposed DINN, we design a parallel Feature Aware Projection Module (FAPM) to assist DINN in preserving essential tag information, thereby improving extraction accuracy. In addition, we introduce a Distance Metric-Guided Module (DMGM) that learns asymmetric one-class representations, enabling the dual-tags to exhibit different robustness performances under malicious manipulations. Extensive experiments on diverse datasets and unseen manipulations demonstrate that the proposed tagging approach achieves promising performances on both authenticity verification and source tracing for reliable fake news detection and outperforms the prior works.

Semantic communication (SemCom) has recently gained attention for its ability to achieve high transmission efficiency with minimal data distortion under limited communication resources. However, the strong correlation between source data and channel input leaves SemCom schemes vulnerable to eavesdropping. Additionally, advances in quantum computing threaten traditional cryptographic methods such as RSA due to Shor’s algorithm. To address these risks, a secure SemCom framework with post-quantum protection is essential. This paper presents a post-quantum secure semantic communication (PQSC) framework by integrating learning with errors (LWE) encryption (widely regarded as quantum-resistant) into a VQ-VAE-based SemCom system. The proposed PQSC framework not only resists quantum attacks but also defends against chosen-plaintext attacks. Experiments show that PQSC consistently outperforms baseline methods across various datasets, channel conditions, and SNR levels. To simulate practical wireless environments, we implement channel coding and modulation using Nvidia Sionna, a GPU-accelerated library for physical layer research. We further examine the trade-off between compression efficiency and computational cost. A downlink use case is modeled to analyze recovery quality, energy consumption, and latency. Our mathematical analysis offers insights into system design and parameter selection for real-world deployment.

This paper addresses the security and privacy issues of the global models in Federated Learning by proposing a new approach, called PDFL, which tackles the challenges of poisoning attacks and privacy leakage in FL rounds. PDFL is based on secure multi-party computation and performs privacy-preserving cluster analysis on encrypted data from participants in order to identify malicious poisoning attackers. This approach involves a two-server mechanism and integrates four privacy-preserving protocols based on two-party computation (2PC): SecJudge for normalizing gradients, SecCosine for computing the cosine similarity values among gradients, SecClu for countering poisoning attacks, and SecAgg for secure aggregation by the server. These protocols are designed to achieve low computational costs, preserve client data privacy, and mitigate poisoning attacks from the potentially malicious clients. We provide a theoretical proof that our four sub-protocols and the PDFL scheme are both safe and reliable, demonstrating that PDFL can ensure the privacy and security of the participating data. Additionally, we conduct extensive simulation experiments to evaluate the accuracy, efficiency, computational overhead, and communication overhead associated with the PDFL scheme. Experimental results show the potential of the PDFL scheme in significantly enhancing the ability to identify malicious poisoning attackers in federated learning systems accurately and efficiently, hence making PDFL a promising solution for addressing privacy and security concerns in this domain.

With the evolution of artificial intelligence-generated content (AIGC) techniques and the development of space-air-ground integrated networks (SAGIN), there will be a growing opportunity to enhance mobile user experiences with customized AIGC applications. This is enabled by combining parameter-efficient fine-tuning (PEFT) with mobile edge computing. In this paper, we formulate the optimization problem of maximizing the parameter training efficiency of the SAGIN system over wireless networks under limited resource constraints. We propose theParameter training efficiencyAwareResourceAllocation (PARA) technique to jointly optimize user association, data offloading, and communication and computational resource allocation. Detailed derivations are presented to solve this difficult sum of ratios problem based on quadratically constrained quadratic programming (QCQP), semidefinite programming (SDP), graph theory, and fractional programming (FP) techniques. Our proposed PARA technique is effective in finding a stationary point of this non-convex problem. The simulation results demonstrate that the proposed PARA method outperforms other baselines.

The rapid proliferation of emerging applications, such as the Metaverse and Artificial Intelligence Generated Content (AIGC), demands extensive computational resources, ultra-low latency, and scalable user support. Traditional terrestrial Mobile Edge Computing (MEC) systems cannot fully satisfy these stringent requirements due to limited coverage and constrained resources. This paper proposes a Satellite-Terrestrial Integrated Network-based Mobile Edge Computing (SMEC) system explicitly positioned within an innovative edge-satellite-cloud continuum, incorporating terrestrial edge servers, satellite servers, and terrestrial cloud servers into a unified resource allocation framework. Unlike previous works, which typically oversimplify system complexities, our heterogeneous SMEC architecture explicitly models diverse user-server interactions, satellite energy constraints, and realistic multi-objective trade-offs among latency, energy consumption, and user experience, which, however, introduces challenging non-convex and discrete variables. We formulate this realistic and complex resource allocation problem as a Mixed-Integer Non-Convex Problem (MINCP) and propose the Connection-constrained SMEC Resource Allocation (CSRA) algorithm. CSRA innovatively integrates Block Coordinate Descent (BCD), Successive Convex Approximation (SCA), and advanced Fractional Programming (FP) techniques with significant algorithmic enhancements to accelerate the convergence speed and reduce the computational overhead. Simulation results demonstrate that the CSRA algorithm significantly outperforms benchmark methods, underscoring its practical effectiveness and methodological robustness.

With large AI systems and models (LAMs) playing an ever-growing role across diverse applications, their impact on the privacy and cybersecurity of critical infrastructure has become a pressing concern. The LAMPS workshop is dedicated to tackling these emerging challenges, promoting dialogue on cutting-edge developments and ethical issues in safeguarding LAMs within critical infrastructure contexts. Bringing together leading experts from around the world, this workshop will delve into the complex privacy and cybersecurity risks posed by LAMs in critical sectors. Attendees will explore innovative solutions, exchange best practices, and contribute to shaping the future research agenda, emphasizing the crucial balance between advancing AI technologies and securing critical digital and physical infrastructures.

There is a recent surge of studies on dynamic-committee proactive secret sharing (DPSS), in which not only will the shares be periodically refreshed (proactive secret sharing), but also the parties who hold the shares will be dynamically changed. It has direct applications in blockchain systems that require committees to manage confidential information, as well as in decentralized storage networks with dynamic participant involvement. Despite substantial attention, DPSS still has high communication complexity, particularly with large-size input data. In this article, we initiate the study of dynamic-committee proactive information dispersal (DPID). From a conceptual perspective, we can regard DPID as DPSS without the requirement for confidentiality. We model and construct DPID schemes with significantly reduced complexity. To demonstrate its efficiency, we also present a general framework for compiling our DPID into DPSS. By integrating our DPID construction, we achieve the first DPSS with much lower communication complexity for large-size data, whose benefits can be clearly shown in our experiments.

To enhance the reliability and credibility of graph neural networks (GNNs) and improve the transparency of their decision logic, a new field of explainability of GNNs (XGNN) has emerged. However, two major limitations severely degrade the performance and hinder the generalizability of existing XGNN methods: they (a) fail to capture the complete decision logic of GNNs across diverse distributions in the entire dataset's sample space, and (b) impose strict prerequisites on edge properties and GNN internal accessibility. To address these limitations, we propose OPEN, a novel cOmprehensive and Prerequisite-free Explainer for GNNs. OPEN, as the first work in the literature, can infer and partition the entire dataset's sample space into multiple environments, each containing graphs that follow a distinct distribution. OPEN further learns the decision logic of GNNs across different distributions by sampling subgraphs from each environment and analyzing their predictions, thus eliminating the need for strict prerequisites. Experimental results demonstrate that OPEN captures nearly complete decision logic of GNNs, outperforms state-of-the-art methods in fidelity while maintaining similar efficiency, and enhances robustness in real-world scenarios.

Audio deepfake detection (ADD) models are commonly evaluated using datasets that combine multiple synthesizers, with performance reported as a single Equal Error Rate (EER). However, this approach disproportionately weights synthesizers with more samples, underrepresenting others and reducing the overall reliability of EER. Additionally, most ADD datasets lack diversity in bona fide speech, often featuring a single environment and speech style (e.g., clean read speech), limiting their ability to simulate real-world conditions. To address these challenges, we propose bona fide cross-testing, a novel evaluation framework that incorporates diverse bona fide datasets and aggregates EERs for more balanced assessments. Our approach improves robustness and interpretability compared to traditional evaluation methods. We benchmark over 150 synthesizers across nine bona fide speech types and release a new dataset to facilitate further research at https://github.com/cyaaronk/audio_deepfake_eval.

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

With the rapid advancement of wireless communication technologies, the scarcity of available spectrum resources has become increasingly pronounced. Dynamic Spectrum Access (DSA) emerges as a promising solution to address this challenge. Traditional DSA methods based on Q-learning emphasize autonomous learning by individual nodes, whereas more recent approaches incorporating Federated Learning (FL) introduce collaborative learning among nodes but remain reliant on a central server. In this paper, we propose a novel DSA scheme based on Swarm Learning (SL), which enables a fully decentralized, distributed machine learning paradigm by establishing a blockchain-based peer-to-peer network. This approach capitalizes on the strengths of SL, facilitating cooperative learning among multiple nodes to enhance DSA performance. By allowing IoT terminals to share model parameters within a blockchain framework, the proposed scheme mitigates the vulnerabilities associated with centralized servers. Simulation results demonstrate that the SL-based DSA scheme not only surpasses the access efficiency of FL-based methods but also obviates the necessity of a central aggregation server. Furthermore, the fully decentralized architecture enhances the auditability of system data, thereby bolstering user privacy protection.

Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users' shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines.

Anomaly detection in human activity recognition (HAR) is a critical subfield that leverages data from the Internet of Things (IoT) to monitor human activities and detect errors or abnormal events. Conventional rule-based approaches often fail to capture the intricate relationships between sensor values, while machine-learning-based methods tend to lack the ability to provide explainability and actionable context for the detected anomalies. In this article, we introduce a novel correlation-based anomaly detection framework designed to improve the security and reliability of IoT-enabled HAR systems. Our proposed scheme utilizes a context-aware deep learning architecture to predict sensor values by leveraging the interdependencies between coexisting sensors in the deployment environment. Experimental results demonstrate that our model achieves a best anomaly prediction accuracy of 99.76% on individual sensors and outperforms other baseline models, consistently maintaining high F1 scores with a minimum of 0.866 on various sensors, even when the training dataset is reduced. Furthermore, we propose an AI-generated content (AIGC)-based visualization method for reporting anomalies, offering clear insights into the context and severity of detected anomalies and their potential system impact.

With the advancement of wireless communication technologies, available spectrum resources are becoming increasingly scarce. Dynamic Spectrum Access (DSA) is one of the effective approaches to address the challenge. Traditional Q-learning DSA relies on node self-learning, while recent Federated Learning (FL) DSA introduces node collaboration but still depends on a central server. This paper proposes a DSA scheme based on Swarm Deep Reinforcement Learning (SDRL), achieving a fully decentralized distributed machine learning through the construction of a blockchain-based peer-to-peer network. This scheme leverages the advantages of swarm learning (SL), utilizing collaborative learning among multiple nodes to enhance DSA performance. IoT terminals share model parameters, utilizing the benefits of blockchain networks to mitigate the risks associated with centralized servers. Simulation results demonstrate that the SDRL scheme not only improves DSA access efficiency compared to FL-based schemes but also eliminates the need for a central aggregation server. The fully decentralization architecture enhances the auditablity of the data in the system which further preserves each user’s privacy.

Federated Unlearning (FU) is gaining prominence for its capability to eliminate influences of specific users’ data from trained global Federated Learning (FL) models. A straightforward FU method involves removing the unlearned user-specified data and subsequently obtaining a new global FL model from scratch with all remaining user data, a process that unfortunately leads to considerable overhead. To enhance unlearning efficiency, a widely adopted strategy employs clustering, dividing FL users into clusters, with each cluster maintaining its own FL model. The final inference is then determined by aggregating the majority vote from the inferences of these sub-models. This method confines unlearning processes to individual clusters for removing the training data of a particular user, thereby enhancing unlearning efficiency by eliminating the need for participation from all remaining user data. However, current clustering-based FU schemes mainly concentrate on refining clustering to boost unlearning efficiency but without addressing the issue of the potential information leakage from FL users’ gradients, a privacy concern that has been extensively studied. Typically, integrating secure aggregation (SecAgg) schemes within each cluster can facilitate a privacy-preserving FU. Nevertheless, crafting a clustering methodology that seamlessly incorporates SecAgg schemes is challenging, particularly in scenarios involving adversarial users and dynamic users. In this connection, we systematically explore the integration of SecAgg protocols within the most widely used federated unlearning scheme, which is based on clustering, to establish a privacy-preserving FU framework, aimed at ensuring privacy while effectively managing dynamic user participation. Comprehensive theoretical assessments and experimental results show that our proposed scheme achieves comparable unlearning effectiveness, alongside offering improved privacy protection and resilience in the face of varying user participation.

Existing research has demonstrated that deep neural networks are susceptible to model extraction attacks, where an attacker can construct a substitute model with similar functionality to the victim model by querying the black-box victim model. To counter such attacks, various disruption-based defenses have been proposed. These defenses disrupt the output results of queries before returning them to potential attackers. In this paper, we propose the first defense-penetrating model extraction attack framework, aimed at breaking disruption-based defense methods. Our proposed attack framework comprises two key modules: disruption detection and disruption recovery, which can be integrated into generic model extraction attacks. Specifically, the disruption detection module uses a novel meta-learning-based algorithm to infer the defense strategy employed by the defender, by learning the key differences between the distributions of disrupted and undisrupted query results. Once the defense method is inferred, the disruption recovery module is designed to restore clean query results from the disrupted query results, using a carefully-designed generative model. We conducted extensive experiments on 5 commonly-used datasets to evaluate the effectiveness of our proposed framework. The results demonstrate that the substitute model accuracy of current model extraction attacks can be significantly improved by up to 82.42%, even when faced with four state-of-the-art model extraction defenses. Moreover, our attack approach shows promising results in penetrating unknown defenses in real-world cloud service APIs hosted by Microsoft Azure and Face++.

The rapid growth of electric vehicle and autonomous vehicle populations has led to explosive expansion of IoV data being transmitted in the wireless communication infrastructure. Advances in IoV technologies also resulted in more complex and dynamic communication protocols/patterns, which are hard for the underlying wireless network to satisfy. Besides, security considerations of IoV communications require that key management must be stringently prohibit global failure mode of key management, meaning that, if a single IoV node compromises its private key, it will not lead to total security failure of the entire IoV network. To address these issues, in this paper, we propose a heterogeneous parallel key-insulated multi-receiver signcryption scheme for IoV (HPKI-MRSC). Firstly, the proposed scheme can realize one-to-many heterogeneous transmission, in which RSUs are deployed on certificateless cryptography (CLC) system, while vehicles are allocated in identity-based cryptography (IBC) system. In this manner, we observe that message transmission efficiency is improved greatly. Secondly, the parallel key-insulated mechanism can employ two helper keys to update private key periodically, and then solve key disclosure problem. Finally, when the number of receiver n is greater than or equal to 3, the proposed scheme has a lower signcryption overhead than other comparative schemes, and thus it is more suitable for IoV.

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model. Although various methods exist for detecting such clients in FL, identifying malicious clients requires sufficient model updates, and hence by the time malicious clients are detected, FL models have already been poisoned. Thus, a method is needed to recover an accurate global model after malicious clients are identified. Current recovery methods rely on (i) all historical information from participating FL clients and (ii) the initial model unaffected by the malicious clients, both leading to a high demand for storage and computational resources. In this paper, we show that highly effective recovery can still be achieved based on 1) selective historical information rather than all historical information and 2) a historical model that has not been significantly affected by malicious clients rather than the initial model. In this scenario, we can accelerate the recovery speed and decrease memory consumption while maintaining comparable recovery performance. Following this concept, we introduce Crab (Certified Recovery from Poisoning Attacks and Breaches), an efficient and certified recovery method, which relies on selective information storage and adaptive model rollback. Theoretically, we demonstrate that the difference between the global model recovered by Crab and the one recovered by train-from-scratch can be bounded under certain assumptions. Our experiments, performed across four datasets with multiple machine learning models and aggregation methods, involving both untargeted and targeted poisoning attacks, demonstrate that Crab is not only accurate and efficient but also consistently outperforms previous approaches in recovery speed and memory consumption.

Federated unlearning has become an attractive approach to address privacy concerns in collaborative machine learning, for situations when sensitive data are remembered by AI models during the machine learning process. It enables the removal of specific data influences from trained models, aligning with the growing emphasis on the “right to be forgotten.” While extensively studied in horizontal federated learning, unlearning in vertical federated learning (VFL) remains challenging due to the distributed feature architecture. VFL unlearning includes sample unlearning that removes specific data points’ influence and label unlearning that removes entire classes. Since different parties hold complementary features of the same samples, unlearning tasks require cross-party coordination, creating computational overhead and feature interdependencies. To address such challenges, we propose FedORA (Federated Optimization for data Removal via primal-dual Algorithm), designed for sample and label unlearning in VFL. FedORA formulates the removal of certain samples or labels as a constrained optimization problem solved using a primal-dual framework. Our approach introduces a new unlearning loss function that promotes classification uncertainty rather than misclassification. An adaptive step size enhances convergence, while an asymmetric batch design handles unlearning and retained data efficiently to reduce computational costs, considering the prior influence of the remaining data on the model. We provide theoretical analysis proving that the model difference between FedORA and Train-from-scratch is bounded, establishing guarantees for unlearning effectiveness. Experiments on tabular and image datasets demonstrate that FedORA achieves unlearning effectiveness and utility preservation comparable to Train-from-scratch with reduced computation and communication overhead.

In recent years, Federated Unlearning (FU) has gained attention for addressing the removal of a client’s influence from the global model in Federated Learning (FL) systems, thereby ensuring the “right to be forgotten” (RTBF). State-of-the-art methods for unlearning use historical data from FL clients, such as gradients or locally trained models. However, studies have revealed significant information leakage in this setting, with the possibility of reconstructing a user’s local data from their uploaded information. Addressing this, we propose Starfish, a privacy-preserving federated unlearning scheme using Two-Party Computation (2PC) techniques and shared historical client data between two non-colluding servers. Starfish builds upon existing FU methods to ensure privacy in unlearning processes. To enhance the efficiency of privacy-preserving FU evaluations, we suggest 2PC-friendly alternatives for certain FU algorithm operations. We also implement strategies to reduce costs associated with 2PC operations and lessen cumulative approximation errors. Moreover, we establish a theoretical bound for the difference between the unlearned global model via Starfish and a global model retrained from scratch for certified client removal. Our theoretical and experimental analyses demonstrate that Starfish achieves effective unlearning with reasonable efficiency, maintaining privacy and security in FL systems.

Deep hashing has been widely used in image retrieval tasks, while deep hashing networks are vulnerable to adversarial example attacks. To improve the deep hashing networks’ robustness, it is essential to investigate adversarial attacks on the networks, especially targeted attacks. Among the existing targeted attacks for hashing, the generation-based targeted attack methods have attracted increasing attention due to their efficiency in generating adversarial examples. However, these methods supervise the generation of adversarial examples solely with the hash codes of positive samples, without employing the hash codes of all points in the training set to directly participate in supervisory training, thereby making the attack less effective. Since the hash codes of the training set samples are generated by a well-trained hashing model, these hash codes retain rich semantic information of their corresponding samples, highlighting the necessity of sufficiently utilizing them. Therefore, in this paper, we propose a targeted attack method that utilizes all points’ hash codes in the training set to guide the generation of adversarial attack examples directly. Specifically, we first decode the target label to obtain the corresponding feature map. Then, we concatenate the feature map with the query image and feed them into an encoder-decoder network that employs a skip-connection strategy to obtain a perturbed example. Furthermore, to guide adversarial example generation, we introduce a loss function that exploits the similarities between the perturbed example’s hash code and all points’ hash codes in the training set, thereby making sufficient utilization of the rich semantic information in these hash codes. Experimental results illustrate that our method outperforms the state-of-the-art targeted attack methods in targeted attack effectiveness and transferability. The code is available athttps://github.com/rongxintu3/APGA.

The CAN bus is the most widely used bus for intra-vehicle communication due to its high transmission stability, excellent real-time communication capability, and relatively low cost. As the number of ECUs grows, the CAN bus load increases and thus raises the possibility of data transmission delays and errors. Message compression based on the differential algorithm has been proposed to reduce the CAN bus load. However, current works do not consider the security problems of the CAN bus. Attackers can manage to acquire the original messages before compression and disturb the message statistics to decrease compression rate by injecting malicious frames. In this paper, we propose a secure compression mechanism for the intra-vehicle network, including an improved compression algorithm, a stream key distribution scheme, and a hierarchical encryption scheme. Formal verification results show that the proposed scheme can achieve mutual authentication, message confidentiality and integrity, resist replay attacks, and support secure compression. Evaluations using real vehicle data on 16 MHz boards show the average communication overhead can be reduced by 46.38% compared to the original messages. Performance analysis results show our scheme can reduce computational overhead on compression by 31.82% and 19.43% on decompression compared to related schemes.

Unmanned aerial vehicles (UAVs) equipped with high line-of-sight communications have been explored as a complement to emergency communication vehicles (ECVs), particularly when ground Internet of Vehicles (IoVs) is dysfunctional resulting from natural disasters. To protect the communication security and integrity of this air-ground integrated networks created in an untrusted and open wireless environment, authentication and key agreement (AKA) is an essential mechanism to establish a secure communication channel by negotiating a session key. Nonetheless, general AKA protocols are typically not ideal for time-sensitive and computing-intensive UAVs-assisted IoVs emergency rescue, in that they are unable to simultaneously satisfy efficiency and key security requirements including accountability, resilience, thresholds changeability, shares verifiability, group adaptability, and key update. To address this challenge, this paper proposes an accountable group authentication and key agreement (GAKA) protocol with changeable thresholds and verifiable shares supporting adaptive group memberships and updatable keys (i.e. SecER). To safeguard accurate rescue decisions for ground ECVs enabled by reliable collaboration among multiple UAVs, we propose a pseudonym mechanism that aims to provide accountability for UAVs. To achieve resilience and thresholds changeability, our SecER utilizes secret sharing coupled with random parameters to seamlessly transform our GAKA protocol into one running with a new threshold in one round (i.e. round-optimal), rather than two rounds. Finally, verifiable parameters and updatable keys are respectively applied to counter deception attacks caused by maliciously distributed shares and to support adaptive network topology (i.e. UAVs joining and leaving). Extensive simulations show that compared to the state-of-the-art approaches, our SecER is superior in balancing security and efficiency.

Extensive studies have revealed that deep neural networks (DNNs) are vulnerable to adversarial attacks, especially black-box ones, which can heavily threaten the DNNs deployed in the real world. Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existing black-box attack methods still suffer from unsatisfactory performance due to the vast number of queries needed to optimize desired perturbations. Besides, the other critical challenge is that adversarial examples built in a noise-adding manner are abnormal and struggle to successfully attack robust models, whose robustness is enhanced by adversarial training against small perturbations. There is no doubt that these two issues mentioned above will significantly increase the risk of exposure and result in a failure to dig deeply into the vulnerability of DNNs. Hence, it is necessary to evaluate DNNs' fragility sufficiently under query-limited settings in a non-additional way. In this paper, we propose the Spatial Transform Black-box Attack (STBA), a novel framework to craft formidable adversarial examples in the query-limited scenario. Specifically, STBA introduces a flow field to the high-frequency part of clean images to generate adversarial examples and adopts the following two processes to enhance their naturalness and significantly improve the query efficiency: a) we apply an estimated flow field to the high-frequency part of clean images to generate adversarial examples instead of introducing external noise to the benign image, and b) we leverage an efficient gradient estimation method based on a batch of samples to optimize such an ideal flow field under query-limited settings. Compared to existing score-based black-box baselines, extensive experiments indicated that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate under query-limited settings.

Auditability and verifiability are critical elements in establishing trustworthiness in federated learning (FL). These principles promote transparency, accountability, and independent validation of FL processes. Incorporating auditability and verifiability is imperative for building trust and ensuring the robustness of FL methodologies. Typical FL architectures rely on a trustworthy central authority to manage the FL process. However, reliance on a central authority could become a single point of failure, making it an attractive target for cyber-attacks and insider frauds. Moreover, the central entity lacks auditability and verifiability, which undermines the privacy and security that FL aims to ensure. This article proposes an auditable and verifiable decentralized FL (DFL) framework. We first develop a smart-contract-based monitoring system for DFL participants. This monitoring system is then deployed to each DFL participant and executed when the local model training is initiated. The monitoring system records necessary information during the local training process for auditing purposes. Afterward, each DFL participant sends the local model and monitoring system to the respective blockchain node. The blockchain nodes representing each DFL participant exchange the local models and use the monitoring system to validate each local model. To ensure an auditable and verifiable decentralized aggregation procedure, we record the aggregation steps taken by each blockchain node in the aggregation contract. Following the aggregation phase, each blockchain node applies a multisignature scheme to the aggregated model, producing a globally verifiable model. Based on the signed global model and the aggregation contract, each blockchain node implements a consensus protocol to store the validated global model in tamper-proof storage. To evaluate the performance of our proposed model, we conducted a series of experiments with different machine learning architectures and datasets, including CIFAR-10, F-MNIST, and MedMNIST. The experimental results indicate a slight increase in time consumption compared with the state-of-the-art, serving as a tradeoff to ensure auditability and verifiability. The proposed blockchain-enabled DFL also saves up to 95% communication costs for the participant side.

Low Earth orbit (LEO) satellite systems play an important role in next generation communication networks due to their ability to provide extensive global coverage with guaranteed communications in remote areas and isolated areas where base stations cannot be cost-efficiently deployed. With the pervasive adoption of LEO satellite systems, especially in the LEO Internet-of-Things (IoT) scenarios, their spectrum resource management requirements have become more complex as a result of massive service requests and high bandwidth demand from terrestrial terminals. For instance, when leasing the spectrum to terrestrial users and controlling the uplink transmit power, satellites collect user data for machine learning purposes, which usually are sensitive information such as location, budget and quality of service (QoS) requirement. To facilitate model training in LEO IoT while preserving the privacy of data, blockchain-driven federated learning (FL) is widely used by leveraging on a fully decentralized architecture. In this paper, we propose a hybrid spectrum pricing and power control framework for LEO IoT by combining blockchain technology and FL. We first design a local deep reinforcement learning algorithm for LEO satellite systems to learn a revenue-maximizing pricing scheme. Then the agents collaborate to form an FL system. We also propose a reputation-based blockchain which is used in the global model aggregation phase of FL to optimize the power control. Based on the reputation mechanism, a node is selected for each global training round to perform model aggregation and block generation, which can further enhance the decentralization of the network and guarantee the trust. Simulation tests are conducted to evaluate the performances of the proposed scheme. Our results show the efficiency of finding the maximum revenue scheme for LEO satellite systems while preserving the privacy of each agent.

Semantic communication (SemCom) is an emerging way that aims to improve communication efficiency based on the semantics of content, which relies on the knowledge base (KB) and is usually dedicated to specific tasks or datasets. To improve the adaptability of SemCom systems on unknown datasets, we propose a post-deployment Fine-Tunable Semantic Communication (FTSC) system for image transmission. Towards an adaptive and efficient SemCom system, our research consists of the framework design of FTSC and its system optimization study. Firstly, the generalizability study is conducted based on a two-layer hierarchical vector quantized-variational autoencoder (VQ-VAE-2). Unlike traditional SemCom that can work on limited pretrained datasets, FTSC adapts to varied input data post-deployment, enhancing practicality in diverse communication scenarios. This system incorporates two novel fine-tuning methods: Decoder Fine-Tuning (DFT) and Latent Space-based Decoder Fine-Tuning (LSDFT). DFT updates the decoder for new images post-deployment without transmitting gradients, while LSDFT eliminates the need for raw image transmission during fine-tuning. Secondly, we study the system optimization of the proposed FTSC framework to improve the efficiency of communication resource allocation with the concern of recovery quality, time delay, and energy cost in downlink transmissions. Extensive experiments demonstrate the superiority of FTSC over Joint Photographic Experts Group (JPEG) and Joint Source-Channel Coding (JSCC) across various datasets and noise levels, and both DFT and LSDFT significantly enhance image recovery on unfamiliar datasets compared to pre-trained models.

Federated Learning (FL) has been widely used to train shared machine learning models while addressing the privacy concerns. When deployed in wireless networks, bandwidth resources limitation is a key issue, thereby necessitating device scheduling and bandwidth allocation. It is challenging to carry out device scheduling due to the large combinatorial search space. Besides, the heterogeneous computing capabilities and uncertain channel states of wireless devices complicate the design of a bandwidth allocation method. In this paper, we propose a joint device scheduling and bandwidth allocation framework for implementing FL in wireless networks. Specifically, deep reinforcement learning (DRL) is employed to conduct device scheduling. To this end, the state space, action space, and reward function of DRL are carefully defined for a typical FL system. Long short-term memory (LSTM) is adopted as the DRL agent to analyze the sequential input data. Given the scheduled devices of each global iteration, the proposed bandwidth allocation method aims to minimize the weighted sum of the time delay and energy consumption. Numerical experiments on both independent and identically distributed (IID) and non-IID datasets demonstrate that the proposed framework enables FL to reach the desired accuracy with low time delay and energy consumption.

Federated unlearning (FU) offers a promising solution to effectively address the need to erase the impact of specific clients’ data on the global model in federated learning (FL), thereby granting individuals the "Right to be Forgotten". The most straightforward approach to achieve unlearning is to train the model from scratch, excluding clients who request data removal, but it is resource-intensive. Current state-of-the-art FU methods extend traditional FL frameworks by leveraging stored historical updates, enabling more efficient unlearning than training from scratch. However, the use of stored updates introduces significant privacy risks. Adversaries with access to these updates can potentially reconstruct clients’ local data, a well-known vulnerability in the privacy domain. While privacy-enhanced techniques exist, their applications to FU scenarios that balance unlearning efficiency with privacy protection remain underexplored. To address this gap, we propose FedADP, a method designed to achieve both efficiency and privacy preservation in FU. Our approach incorporates an adaptive differential privacy (DP) mechanism, carefully balancing privacy and unlearning performance through a novel budget allocation strategy tailored for FU. FedADP also employs a dual-layered selection process, focusing on global models with significant changes and client updates closely aligned with the global model, reducing storage and communication costs. Additionally, a novel calibration method is introduced to facilitate effective unlearning. Extensive experimental results demonstrate that FedADP effectively manages the trade-off between unlearning efficiency and privacy protection.

Transfer of knowledge across domains is the focus for cross-domain and multi-domain fake news detection. However, most of the existing methods based on cross-domain knowledge transfer have two issues: (1) they usually ignore domain-specific features; (2) they are less effective in handling the imbalanced data distribution across domains. Targeting these two issues, we focus on how to effectively leverage user-news engagements in both data-richer and data-sparser domains. This is because not only users' engagement characteristics closely relate to the veracity of the engaged news, but also there are consistent patterns in common users' engagements with news across domains. Considering these two insights, this work aims to perform dual-target cross-domain fake news detection via well modeling users' engagement patterns. In particular, it aims to transfer knowledge based on user-news engagements for handling the imbalanced data distribution across domains, which is novel but challenging. To this end, in this paper, we propose a novel framework to mine User-news engagement Patterns for DuAl-TargEt cross-domain fake news detection (UPDATE). In UPDATE, we first mine user-news engagement patterns as the key auxiliary information for cross-domain knowledge transfer. In such a way, it avoids the necessity to remove the domain-specific news information, and thereby, better preserve useful news information. Then, we combine engagement features of common users in both data-richer and data-sparser domains. By doing so, UPDATE improves the information richness in each of the two domains, thus improving detection performance in both domains when detecting news from domains with imbalanced data distribution. Extensive experiments conducted on real-world datasets demonstrate that UPDATE significantly outperforms state-of-the-art cross-domain and multi-domain methods as well as large language models (LLMs), such as GPT-3.5-turbo in terms of AUC and Fl-score for fake news detection.

The Matthew effect is a big challenge in Recommender Systems (RSs), where popular items tend to receive increasing attention, while less popular ones are often overlooked, perpetuating existing disparities.Although many existing methods attempt to mitigate Matthew effect in the static or quasi-static recommendation scenarios, such issue will be more pronounced as users engage with the system over time.To this end, we propose a novel framework, Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation (HiCore), aiming to address Matthew effect in the Conversational Recommender System (CRS) involving the dynamic user-system feedback loop.It devotes to learn multi-level user interests by building a set of hypergraphs (i.e., item-, entity-, word-oriented multiple-channel hypergraphs) to alleviate the Matthew effec.Extensive experiments on four CRS-based datasets showcase that HiCore attains a new state-of-the-art performance, underscoring its superiority in mitigating the Matthew effect effectively.Our code is available at https://github.com/zysensmile/HiCore.

Modern vehicles are equipped with ECU nodes and intra-vehicle buses. Among these, the CAN bus stands out as the most widely utilized intra-vehicle bus due to its affordability and straightforward deployment. However, the CAN bus suffers from significant security vulnerabilities, such as the absence of access control, identity authentication, message encryption, and authentication. In this paper, we propose a lightweight message-based key distribution scheme aimed at addressing these vulnerabilities. Our scheme facilitates mutual authentication during key distribution and assigns a unique key to each class of message. Formal verification using the Scyther tool demonstrates that our protocol achieves mutual authentication and effectively mitigates several protocol attacks, including replay, tampering, and manin-the-middle attacks. We evaluate our scheme using Arduino UNO boards. Performance analysis indicates that our scheme exhibits superior security capabilities compared to other related schemes and outperforms them in terms of communication and computation overheads.

Most face anti-spoofing methods address the generalization problem by extracting domain-invariant representations from multiple source domains or unlabelled target data. However, their deployment in real-world applications is unfeasible when data is insufficient or unavailable due to the collection costs and privacy concerns. This work investigates a more practical yet challenging scenario: single-source domain generalization based face anti-spoofing, where only one source domain is available during training and evaluated on multiple unseen target domains. To tackle this problem, a Causality-inspired Single-source Domain Generalization method (CSDG) is developed, which focuses on learning causal spoofing representations from the causality perspective. Specifically, a causal diagram is constructed to estimate the fundamental properties of ideal causal spoofing representations: remain invariant to shifts of domain-related confounders and causally sufficient for the detection category. To satisfy the above properties, the Causal Learning Module (CLM) maximizes the correlation of representations before and after intervention and minimizes the correlation with negative distributions. The intervention is achieved by arbitrarily performing spectrum mixup and structure destruction on source data within the Causal Intervention Model (CIM). Extensive experiments on four benchmark datasets validate the effectiveness of the proposed method.

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial examples (AEs), which brings a huge security risk to the application of DNNs, especially for the AI models developed in the real world. To impede the process of fully exploiting the vulnerabilities of existing DNNs and further improving their robustness in the face of such malicious inputs, many attack methods have been proposed to build AEs. Despite the significant progress that has been made recently, existing attack methods still suffer from the unsatisfactory performance of escaping from being detected by naked human eyes due to the formulation of AE heavily relying on a noise-adding manner. Such mentioned challenges will significantly increase the risk of exposure and result in an attack to be failed. Therefore, in this paper, we propose the Salient Spatially Transformed Attack (SSTA), a novel framework to craft imperceptible AEs, which enhance the stealthiness of AEs by estimating a smooth spatial transform metric on a most critical area to generate AEs instead of adding external noise to the whole image. Compared to SOTA baselines, extensive experiments indicated that SSTA could effectively improve the imperceptibility of the AEs while maintaining a 100% attack success rate.

With the rapid development of low-cost consumer electronics and cloud computing, Internet-of- Things (IoT) devices are widely adopted for supporting next-generation distributed systems such as smart cities and industrial control systems. IoT devices are often susceptible to cyber attacks due to their open deployment environment and limited computing capabilities for stringent security controls. Hence, Intrusion Detection Systems (IDS) have emerged as one of the effective ways of securing IoT networks by monitoring and detecting abnormal activities. However, existing IDS approaches rely on centralized servers to generate behaviour profiles and detect anomalies, causing high response time and large operational costs due to communication overhead. Besides, sharing of behaviour data in an open and distributed IoT network environment may violate on-device privacy requirements. Additionally, various IoT devices tend to capture heterogeneous data, which complicates the training of behaviour models. In this paper, we introduce Federated Learning (FL) to collaboratively train a decentralized shared model of IDS, without exposing training data to others. Furthermore, we propose an effective method called Federated Learning Ensemble Knowledge Distillation (FLEKD) to mitigate the heterogeneity problems across various clients. FLEKD enables a more flexible aggregation method than conventional model fusion techniques. Experiment results on the public dataset CICIDS2019 demonstrate that the proposed approach outperforms local training and traditional FL in terms of both speed and performance and significantly improves the system's ability to detect unknown attacks. Finally, we evaluate our proposed framework's performance in three potential real-world scenarios and show FLEKD has a clear advantage in experimental results.

Emerging Internet of Things (IoT) platforms provide sophisticated capabilities to automate IoT services by enabling occupants to create trigger-action rules. Multiple trigger-action rules can physically interact with each other via shared environment channels, such as temperature, humidity, and illumination. We refer to inter-rule interactions via shared environment channels as a physical inter-rule vulnerability. Such vulnerability can be exploited by attackers to launch attacks against IoT systems. We propose a new framework to proactively discover possible physical inter-rule interactions from user requirement specifications (i.e., descriptions) using a deep learning approach. Specifically, we utilize the Transformer model to generate trigger-action rules from their associated descriptions. We discover two types of physical inter-rule vulnerabilities and determine associated environment channels using natural language processing (NLP) tools. Given the extracted trigger-action rules and associated environment channels, an approach is proposed to identify hidden physical inter-rule vulnerabilities among them. Our experiment on 27983 IFTTT style rules shows that the Transformer can successfully extract trigger-action rules from descriptions with 95.22% accuracy. We also validate the effectiveness of our approach on 60 SmartThings official IoT apps and discover 99 possible physical inter-rule vulnerabilities.

Federated learning facilitates collaborative machine learning, enabling multiple participants to collectively develop a shared model while preserving the privacy of individual data. The growing importance of the “right to be forgotten” calls for effective mechanisms to facilitate data removal upon request. In response, federated unlearning (FU) has been developed to efficiently eliminate the influence of specific data from the model. Current FU methods primarily rely on approximate unlearning strategies, which seek to balance data removal efficacy with computational and communication costs, but often fail to completely erase data influence. To address these limitations, we propose FedUHB, a novel exact unlearning approach that leverages the Polyak heavy ball optimization technique, a first-order method, to achieve rapid retraining. In addition, we introduce a dynamic stopping mechanism to optimize the termination of the unlearning process. Our extensive experiments show that FedUHB not only enhances unlearning efficiency but also preserves robust model performance after unlearning. Furthermore, the dynamic stopping mechanism effectively reduces the number of unlearning iterations, conserving both computational and communication resources. FedUHB can be proved as an effective and efficient solution for exact data removal in federated learning settings.

Low Earth orbit (LEO) satellite systems are receiving increasing attention as they provide extensive global coverage. Secure and efficient management of limited spectrum bands and power resources are crucial for controlling operational costs and ensuring reliable communication in LEO satellite systems. However, spectrum pricing and power control optimization are challenging tasks. First, dynamic pricing is needed for leasing idle satellite spectrum to terrestrial users, as it must consider user mobility and real-time demand changes. Additionally, there is a trust concern that when utilizing the leased spectrum, terrestrial users may maliciously exceed limited transmit power to improve the quality of service (QoS). Moreover, users' privacy should be protected because the data collected by satellites often contain sensitive information such as location, budget, and QoS needs. In this paper, we propose a hybrid spectrum pricing and power control framework for LEO satellite-enabled networks to mitigate the above concerns by combining blockchain technology and Federated Learning (FL). We first design a local deep reinforcement learning algorithm for LEO satellite systems to learn a revenue-maximizing pricing strategy and power control scheme. Subsequently, these individual agents collaborate to establish an FL system without sharing their sensitive raw data. We also propose a reputation-based blockchain used in the global model aggregation phase to further enhance the traceability of the network and guarantee the trust. We conduct simulation tests to evaluate the efficacy of the proposed scheme, and our results show its capability to efficiently find the maximum revenue scheme for LEO satellite systems while preserving the privacy of each participating agent in an auditable mode.

Knowledge removal is a crucial task in AI safety and for aligning with the Right To Be Forgotten (RTBF) principle. Machine Unlearning (MU) is an important means for achieving knowledge removal by removing the ML impacts of a specified subset of training data. However, existing MU frameworks may be misused to facilitate emerging novel poisoning attacks, where adversaries may introduce both poisoned data and the corre-sponding mitigation data that temporarily neutralize the effects of the poisoned data. The adversaries then submit malicious unlearning requests for the mitigation data, hence maintaining the malicious effects of the poison. Such attacks have been shown to be effective in single-model scenarios; however, their impacts on ensemble models, which are widely adopted because of their robustness, remain underexplored. Recognizing this gap, we extend these emerging poisoning attacks to ensemble settings to better understand and address the potential risks of malicious unlearning. Our extensive experimental results show that the proposed extended poisoning attacks are effective also in the ensemble settings, achieving a high attack success rate, highlighting the importance of continued research in safeguard measures against misuse of MU as one of the important requirements of AI safety.

Community detection refers to mechanisms that aim to identify groups of interacting nodes in a network according to the structural properties of the network. It has been used to analyze various graphs. In the context of social networks, it requires the collection of each user's social relations, posing the risk of user privacy intrusion caused by untrusted servers. Local differential privacy is a widely adopted approach for providing privacy protection while allowing acceptable utility of the protected data for analytics. There has been growing research interest in applying local differential privacy protection to community detection. However, such protection approaches typically suffer from poor accuracy due to the excessive noise in the protected data. This paper proposes LDP-Cd, a two-phase community detection framework under local differential privacy. LDP-Cd initializes the community groups using the Louvain community detection algorithm and iteratively refines the community in the second phase. Besides, we propose an order-consistent data perturbation method over the degree vector, thus ensuring the ordering consistency of the fitness between the user and community groups, thereby improving the accuracy of community detection. Experimental results on real datasets show that LDP-Cd has significant advantages over existing methods regarding community detection accuracy and a trade-off between user privacy and community detection utility.

Mobile crowdsourcing (MCS) is an emerging paradigm that enables the outsourcing of a complex task to a group of mobile devices. The ability to utilize the collective power of mobile devices and human intelligence makes MCS a significant tool in various scenarios. Nevertheless, it faces practical challenge in protecting user privacy due to the sensitive nature of information collected by mobile devices. Additionally, the inherent openness of MSC and the heterogeneity of mobile devices raise reliability concerns among participants. To address these challenges, by integrating Federated Learning with the pairwise additive masking technique and the Chinese Remainder Theorem, we propose a Blockchain-based Privacy-preserving Federated Learning (BPFL) framework for mobile crowdsourcing, which allows mobile participants to collaboratively solve a crowdsourced machine learning task while preserving privacy. Besides, it employs blockchain technology to record the training process in a transparent and tamper-proof ledger. This ledger guarantees the verifiability of aggregation results and the fair distribution of training rewards, thereby enhancing trust and fairness. We prove that our BPFL supports privacy protection and trust mechanism simultaneously and resists inference and collusion attacks. Experimental results show that our BPFL can achieve high performance in terms of computation cost, communication cost and model accuracy, which is friendly for mobile users with resource-constrained devices in MCS ecosystems.

For unmanned aerial vehicles (UAVs)-assisted post-disaster emergency communication networks, UAVs serves as relay nodes of air-based backup network to support transmission of rescue messages to emergency communication vehicles (ECVs), while ECVs provide on-site ground communication and connectivity to the command center (CC) of the rescue operation. Existing works seldom emphasize communication security such as authenticity of communicating parties and integrity of message content. In this connection, authentication and key agreement (AKA) protocols are promising solutions for achieving communication security. However, the traditional approaches to endpoint security and entity authentication of principals may not be practical in emergency situations, in which network equipment and security modules are exposed to an open and untrusted physical environment. Besides, there is a lack of attention to the study of privacy impacts resulted from the physical loss of UAVs. More importantly, cyber attacks and excessive overhead may deteriorate AKA availability. Motivated by above challenges, we propose an AKA protocol, namely AKAEC, which is based on three-factor (i.e. smart card, biometrics, and password) and physically unclonable function (PUF) for protecting UAVs-assisted emergency communication. Specifically, AKAEC includes ECV-to-UAV (E2U) and UAV-to-UAV (U2U), where the former achieves secure emergency communication between ECV and UAV, while the latter realizes secure emergency communication between UAV and UAV. We then provide a formal security proof under the Real-Or-Random (ROR) model and formal security verification by AVISPA. This is followed by a security analysis to show that AKAEC meets the security goals defined for emergency situations. Finally, the performance of AKAEC is evaluated from communication overhead and computational overhead.

Federated Learning (FL) is a promising machine learning approach for Internet of Things (IoT), but it has to address network congestion problems when the population of IoT devices grows. Hierarchical FL (HFL) alleviates this issue by distributing model aggregation to multiple edge servers. Nevertheless, the challenge of communication overhead remains, especially in scenarios where all IoT devices simultaneously join the training process. For scalability, practical HFL schemes select a subset of IoT devices to participate in the training, hence the notion of device scheduling. In this setting, only selected IoT devices are scheduled to participate in the global training, with each of them being assigned to one edge server. Existing HFL assignment methods are primarily based on search mechanisms, which suffer from high latency in finding the optimal assignment. This paper proposes an improved K-Center algorithm for device scheduling and introduces a deep reinforcement learning-based approach for assigning IoT devices to edge servers. Experiments show that scheduling 50% of IoT devices is generally adequate for achieving convergence in HFL with much lower time delay and energy consumption. In cases where reduction in energy consumption (such as in Green AI) and reduction of messages (to avoid burst traffic) are key objectives, scheduling 30% IoT devices allows a substantial reduction in energy and messages with similar model accuracy.

Internet of Medical Things (IoMTs) is revolutionizing the healthcare industry regarding how diagnosis process takes place, how treatment is provided, and how public health policies are made. A real-world use case of IoMTs is to investigate how infectious diseases, e.g. COVID-19, spread in a population through social events. In this use case, people’s social contact records in certain venues are collected by sensors and saved locally; pandemic modellers, as third-party vendors, are desired to construct social contact network based on contacts records, and to simulate the process of disease transmission over the contact network by transmission modelling; results from the simulation will be provided to authorities for policymaking and pandemic control. However, concerns are raised on data breaches from modellers. In reality, sharing the data in clear with modellers is not allowed by regulations for the sake of privacy. In this work, we will be addressing the contradiction between data privacy and usability when vendors are involved in IoMTs. We propose a secure cloud-edge computing architecture based on an efficient fully homomorphic encryption (FHE) scheme. This architecture allows vendors to securely and “blindly” process medical data without compromising the quality of their service. Moreover, we apply the proposed architecture to the use case of pandemic modelling. By comparisons with a differential privacy-based solution, we demonstrate the favorable feasibility, accuracy and security of the proposed solution.

AI-as-a-Service has emerged as an important trend for supporting the growth of the digital economy. Digital service providers make use of their vast amount of customer data to train AI models (such as image recognition, financial modelling and pandemic modelling etc) and offer them as a service on the cloud. While there are convincing advantages for using such third-party models, the fact that model users are required to upload their data to the cloud is bound to raise serious privacy concerns, especially in the face of increasingly stringent privacy regulations and legislation. To promote the adoption of AI-as-a-Service while addressing privacy issues, we propose a practical approach for constructing privacy-enhanced neural networks by designing an efficient implementation of fully homomorphic encryption. With this approach, an existing neural network can be converted to process FHE-encrypted data and produce encrypted output which are only accessible by the model users, and more importantly, within an operationally acceptable time (e.g. within 1 second for facial recognition in typical border control systems). Experimental results show that in many practical tasks such as facial recognition, text classification and so on, we obtained the state-of-the-art inference accuracy in less than one second on a 16 cores CPU.

In view of inconsistent face acquisition procedure in face anti-spoofing, the detection performance on the target domain generally suffers severe degradation under source-specific gradient optimization. Existing domain adaptation face anti-spoofing methods focus on improving model generalization capability through feature matching, which do not consider the gradient discrepancy between the source and target domains. To this end, this work develops a category-conditional gradient alignment guided face anti-spoofing algorithm (CCGA-FAS) from a novel perspective of gradient discrepancy elimination. Technically, the category-conditional gradient alignment mechanism maximizes the cosine similarity of the gradient vectors generated by source and target samples within the live and spoof categories separately, which promotes the source and target domains to follow similar gradient descent directions during optimization. Considering that the gradient vector generation and alignment is computationally dependent on reliable category information, a temporal knowledge and flexible threshold based dynamic category measurer is devised to provide pseudo category information for unlabelled target samples in an easy-to-hard manner. The optimization for CCGA-FAS is implemented under the teacher-student structure, where the student model serves as the gradient optimization backbone, and the category prediction simultaneously benefits from the teacher and student models to consolidate the alignment stability. Experimental results and analysis demonstrate that the proposed method outperforms the state-of-the-art methods in both unsupervised and K-shot semi-supervised domain adaptive face anti-spoofing scenarios.

Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large number of queries, hence exhibiting limited practical impacts in real-world scenarios. In this paper, we propose a novel black-box attack strategy, Conditional Diffusion Model Attack (CDMA), to improve the query efficiency of generating AEs under query-limited situations. The key insight of CDMA is to formulate the task of AE synthesis as a distribution transformation problem, i.e., benign examples and their corresponding AEs can be regarded as coming from two distinctive distributions and can transform from each other with a particular converter. Unlike the conventionalquery-and-optimizationapproach, we generate eligible AEs with direct conditional transform using the aforementioned data converter, which can significantly reduce the number of queries needed. CDMA adopts the conditional Denoising Diffusion Probabilistic Model as the converter, which can learn the transformation from clean samples to AEs, and ensure the smooth development of perturbed noise resistant to various defense strategies. We demonstrate the effectiveness and efficiency of CDMA by comparing it with nine state-of-the-art black-box attacks across three benchmark datasets. On average, CDMA can reduce the query count to a handful of times; in most cases, the query count is only ONE. We also show that CDMA can obtain > 99% attack success rate for untargeted attacks over all datasets and targeted attack over CIFAR-10 with the noise budget of ϵ = 16.

In this paper, we aim to explore the use of uplink semantic communications with the assistance of UAV in order to improve data collection effiicency for metaverse users in remote areas. To reduce the time for uplink data collection while balancing the trade-off between reconstruction quality and computational energy cost, we propose a hybrid action reinforcement learning (RL) framework to make decisions on semantic model scale, channel allocation, transmission power, and UAV trajectory. The variables are classified into discrete type and continuous type, which are optimized by two different RL agents to generate the combined action. Simulation results indicate that the proposed hybrid action reinforcement learning framework can effectively improve the efficiency of uplink semantic data collection under different parameter settings and outperforms the benchmark scenarios.

Our IoT systems are transforming from “perceptive” to “cognitive,” where connected IoT devices behave as agents and interact with each other in a context-aware manner with minimum human intervention, learning from both the physical environment and experience. New security challenges surface as IoT applications are empowered with more cognitive capability. The vast amount of ever-growing data needed to equip our devices with artificial intelligence puts enormous pressure on the protection of sensitive data flow and the efficiency of network resource utilization. In order to address the potential security challenges for cognitive IoT systems, we first drafted a survey to study the security requirements and challenges of recent IoT proposals for future smart cities and then proposed a differentiated security architecture that enhances security and efficiency for data communication. In the future, we aim to build an incentive mechanism to encourage secure peer-to-peer data sharing using our proposed differentiated security architecture and deep learning techniques.

Threat intelligence and hunting using various logs has evolved into a crucial component of remaining aware of the ever-changing threat landscape. Given the critical need to extract useful intelligence from logs, existing techniques either focus exclusively on isolated records, ignoring correlation and the overall threat scenario, or require significant effort to filter and correlate threat records. Additionally, searching for and matching threat behaviors in logs often involves non-trivial human query construction, impeding fast threat hunting. To address this gap, we present ThreatLand, a system that extracts highlevel intelligence and structured threat patterns from audit logs automatically. ThreatLand is composed of three components (1) A lightweight and accurate NLP pipeline that extracts structured meta-data from alert descriptions and generates a heterogeneous graph that depicts the entire threat scenario. (2) A query execution engine that is both fast and efficient, based on a graphical database. (3) A graphical user interface (GUI) that offers various sorts of interactivity to aid intelligence exploration.We have evaluated the ThreatLand over the dataset containing 9240 real-time EDR alerts collected for the threat events over an enterprise setup in the lab. As a result, ThreatLand presents high-level insights from the alert logs and extracts the valuable threat patterns.

In this paper, we propose – DOT – a hybrid analysis approach designed for the detection and classification of malicious files. We have developed both a unified single model and specialized models tailored to various file extensions. Our solutions leverage byte-level content analysis to identify malicious elements within documents, along with n-gram analysis. The uniqueness of DOT lies in its ability to significantly reduce computational overhead. We achieve this by employing Rolling Encoder Hashing, which shortens bytecode sequences, making them compatible with state-of-the-art sequence models like Recurrent Neural Networks (RNNs). Additionally, we have created a static analysis-based generic model capable of working with a variety of file types, including.doc,.docx,.xls,.xlsx,.pdf, and more. This model can be efficiently deployed in real-world scenarios. Furthermore, we have developed specialized models for different file types, which are enhanced versions of the generic architecture, streamlining complex maintenance procedures. Another key innovation and novelty of DOT lies in exactly locating the portion of content in the byte code that could contain malicious code, to help security analysts make the binary code analysis more efficient.We conducted extensive experiments using a dataset recently made available by sources like VirusShare, Contagio, and others, specifically intended for academic research. Our dataset comprises a substantial collection of over 156,000 documents, encompassing both malicious and benign files of the most hazardous types observed in recent years. Our findings reveal impressive results, with a unified single model achieving a 91.43% accuracy in distinguishing between benign and malicious documents. Furthermore, specialized models tailored to specific file types exhibit even higher accuracy rates: 96.13% for.doc files, 97.85% for.docx files, 92.62% for.xls files, 97.02% for.xlsx files, and 94.11% for.pdf files, respectively and with a very low false positive rate.

Artificial Intelligence-Generated Content (AIGC) refers to the paradigm of automated content generation utilizing AI models. Mobile AIGC services in the Internet of Vehicles (IoV) network have numerous advantages over traditional cloud-based AIGC services, including enhanced network efficiency, better reconfigurability, and stronger data security and privacy. Nonetheless, AIGC service provisioning frequently demands significant resources. Consequently, resource-constrained roadside units (RSUs) face challenges in maintaining a heterogeneous pool of AIGC services and addressing all user service requests without degrading overall performance. Therefore, in this paper, we propose a decentralized incentive mechanism for mobile AIGC service allocation, employing multi-agent deep reinforcement learning to find the balance between the supply of AIGC services on RSUs and user demand for services within the IoV context, optimizing user experience and minimizing transmission latency. Experimental results demonstrate that our approach achieves superior performance compared to other baseline models.

Abstract Collecting and analysing customers' data plays an essential role in the more intense market competition. It is critical to perform data analysis effectively while ensuring the user's privacy, especially after various privacy regulations are enacted. In this paper, we consider the problem of aggregating the stream data generated from wearable devices in a specific time period in a privacy‐preserving manner. Specifically, we adopt the local differential privacy mechanism to provide a strong privacy guarantee for users. One major challenge is that all values of the stream need to be perturbed. The additive noise makes it hard to release an accurate data stream. One way to reduce the noise scale is to select some data points to perturb instead of all. The intuition is that more privacy budgets are applied to a single data point, which ensures the statistical accuracy. The perturbed data points are used to predict the un‐selected data points without consuming an extra privacy budget. Based on this idea, we propose a novel stream data statistical framework, which includes four components, data fitting, skeleton point selection, noisy stream generation, and data aggregation. Extensive experiment results show that our proposed method achieves a much smaller mean square error given a fixed privacy budget compared with the state‐of‐the‐art.

A city is a large human settlement that serves the people who live there, and a smart city is a concept of how cities might better serve their residents through new forms of technology. In this article, we focus on four major smart city domains according to Maslow’s hierarchy of needs: smart utility, smart transportation, smart homes, and smart healthcare. Numerous Internet of Things (IoT) applications have been developed to achieve the intelligence that we desire in our smart domains, ranging from personal gadgets, such as health trackers and smart watches to large-scale industrial IoT systems, such as nuclear and energy management systems. However, many of the existing smart city IoT solutions can be made better by considering the suitability of their security strategies. Inappropriate system security designs generally occur in two scenarios: first, system designers recognize the importance of security but are unsure of where, when, or how to implement it and second, system designers try to fit traditional security designs to meet the smart city security context. Thus, the objective of this article is to provide application designers with the missing security link they may need in order to improve their security designs. By evaluating the specific context of each smart city domain and the context-specific security requirements, we aim to provide directions on when, where, and how they should implement security strategies and the possible security challenges they need to consider. In addition, we present a new perspective on security issues in smart cities from a data-centric viewpoint by referring to the reference architecture, the activity-network-things (ANTs)-centric architecture. This architecture is built upon the concept of “security in a zero-trust environment,” to achieve end-to-end data security. By doing so, we reduce the security risks posed by new system interactions or unanticipated user behaviors while avoiding the hassle of regularly upgrading security models.

Bitcoin is gaining ever increasing popularity. However, professional skills are required if people want to check bitcoin transaction information from the blockchain. As pointed out in a recent study, there is a lack of tools to support effective interactive investigation of bitcoin transactions. Therefore, we present a novel visualization system,BitAnalysis, for interactive bitcoin wallet investigation. The analytical and visualization functions ofBitAnalysisare defined and developed by following the advice and requirements of a group of entrepreneurs and regulators of bitcoin-related business.BitAnalysisprovides a rich set of functions and intuitive visual interfaces for the users, such as law-enforcement officers and regulators, to effectively visualize and analyze the transactions of a bitcoin wallet (i.e., a cluster of bitcoin addresses) and its related wallets, to track the flow of bitcoins, and to identify wallet correlation using our novel clustering functions. To achieve these functions, we have designed new visualization techniques for presenting bitcoin transactions information and introduced theconnection diagramandbitcoin flow mapas new ways of analyzing, tracking and monitoring the trading activities of a cluster of closely related wallets. We also present an extensive user study that validated the effectiveness and usability ofBitAnalysis.

Visible light communication (VLC) is an emerging wireless technology to support high transmission rate for indoor devices by using existing lighting infrastructure, and VLC-based indoor localization is capable of providing high-accuracy localization. However, current VLC-based localization systems suffer from several key challenges such as sensitivity to random tilting of the receiver, which limits its full potential in real-world applications. In this paper, we design an integrated visible light communication and localization (VLCL) system to simultaneously support accurate real-time localization and communication services for indoor devices. To achieve this, an advanced differential phase difference of arrival (A-DPDOA) localization design is developed to simplify hardware and improve tracking robustness. In addition, a joint adaptive modulation, subcarrier and power allocation scheme is also proposed, which aims to improve the communication data rate and localization accuracy. Extensive experiments are performed to demonstrate that the proposed integrated VLCL system achieves higher localization accuracy and transmission data rate, compared to existing systems and schemes. Experiments also illustrate that the localization algorithm is more robust against the random tilting of the receiver under device movement in two-dimensional and three-dimensional scenarios.

In order to remain competitive, Internet companies collect and analyse user data for the purpose of the improvement of user experiences. Frequency estimation is a widely used statistical tool, which could potentially conflict with the relevant privacy regulations. Privacy preserving analytic methods based on differential privacy have been proposed, which require either a large user base or a trusted server. Although the requirements for such solutions may not be a problem for larger companies, they may be unattainable for smaller organizations. To address this issue, we propose a distributed privacy-preserving sampling-based frequency estimation method which has high accuracy even in the scenario with a small number of users while not requiring any trusted server. This is achieved by combining multi-party computation and sampling techniques. We also provide a relation between its privacy guarantee, output accuracy, and the number of participants. Distinct from most existing methods, our methods achievecentralizeddifferential privacy guarantee without the need of any trusted server. We established that, even for a small number of participants, our mechanisms can produce estimates with high accuracy and hence they provide smaller companies with more opportunity for growth through privacy-preserving statistical analysis. We further propose an architectural model to support weighted aggregation in order to achieve a higher accuracy estimate to cater for users with varying privacy requirements. Compared to the unweighted aggregation, our method provides a more accurate estimate. Extensive experiments are conducted to show the effectiveness of the proposed methods.

Machine learning (ML) has been widely recognized as an enabler of the global trend of digital transformation. With the increasing adoption of data-hungry machine learning algorithms, personal data privacy has emerged as one of the key concerns that could hinder the success of digital transformation. As such, Privacy-Preserving Machine Learning (PPML) has received much attention of the machine learning community, from academic researchers to industry practitioners to government regulators. However, organizations are faced with the dilemma that, on the one hand, they are encouraged to share data to enhance ML performance, but on the other hand, they could potentially be breaching the relevant data privacy regulations. Practical PPML typically allows multiple participants to individually train their ML models, which are then aggregated to construct a global model in a privacy-preserving manner, e.g., based on multi-party computation or homomorphic encryption. Nevertheless, in most important applications of large-scale PPML, e.g., by aggregating clients’ gradients to update a global model for federated learning, such as consumer behavior modeling of mobile application services, some participants are inevitably resource-constrained mobile devices, which may drop out of the PPML system due to their mobility nature (Yang et al., 2019). Therefore, the resilience of privacy-preserving aggregation has become an important problem to be tackled because of its real-world application potential and impacts. In this paper, we propose a scalable privacy-preserving aggregation scheme that can tolerate dropout by participants at any time, and is secure against both semi-honest and active malicious adversaries by setting proper system parameters. By replacing communication-intensive building blocks with a seed homomorphic pseudo-random generator, and relying on the additive homomorphic property of Shamir secret sharing scheme, our scheme outperforms state-of-the-art schemes by up to$6.37\times $in runtime and provides a stronger dropout-resilience. The simplicity of our scheme makes it attractive both for implementation and for further improvements.

Face presentation attack detection (PAD) is an essentialmeasure to protect face recognition systems from being spoofed by malicious users and has attracted great attention from both academia and industry. Although most of the existing methods can achieve desired performance to some extent, the generalization issue of face presentation attack detection under cross-domain settings (e.g., the setting of unseen attacks and varying illumination) remains to be solved. In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-modality scenarios. Under the framework, we establish connections between two modality images of genuine faces. Specifically, a novel modality fusion scheme is presented that the image of one modality is translated to the other one through an asymmetric modality translator, then fused with its corresponding paired image. The fusion result is fed as the input to a discriminator for inference. The training of the translator is supervised by an asymmetric modality translation loss. Besides, an illumination normalization module based on Pattern of Local Gravitational Force (PLGF) representation is used to reduce the impact of illumination variation. We conduct extensive experiments on three public datasets, which validate that our method is effective in detecting various types of attacks and achieves state-of-the-art performance under different evaluation protocols.

Machine learning (ML) is a widely accepted means for supporting customized services for mobile devices and applications. Federated Learning (FL), which is a promising approach to implement machine learning while addressing data privacy concerns, typically involves a large number of wireless mobile devices to collect model training data. Under such circumstances, FL is expected to meet stringent training latency requirements in the face of limited resources such as demand for wireless bandwidth, power consumption, and computation constraints of participating devices. Due to practical considerations, FL selects a portion of devices to participate in the model training process at each iteration. Therefore, the tasks of efficient resource management and device selection will have a significant impact on the practical uses of FL. In this paper, we propose a spectrum allocation optimization mechanism for enhancing FL over a wireless mobile network. Specifically, the proposed spectrum allocation optimization mechanism minimizes the time delay of FL while considering the energy consumption of individual participating devices; thus ensuring that all the participating devices have sufficient resources to train their local models. In this connection, to ensure fast convergence of FL, a robust device selection is also proposed to help FL reach convergence swiftly, especially when the local datasets of the devices are not independent and identically distributed (non-iid). Experimental results show that (1) the proposed spectrum allocation optimization method optimizes time delay while satisfying the individual energy constraints; (2) the proposed device selection method enables FL to achieve the fastest convergence on non-iid datasets.

Knowledge Graph Completion (KGC) has been recently extended to multiple knowledge graph (KG) structures, initiating new research directions, e.g. static KGC, temporal KGC and few-shot KGC. Previous works often design KGC models closely coupled with specific graph structures, which inevitably results in two drawbacks: 1) structure-specific KGC models are mutually incompatible; 2) existing KGC methods are not adaptable to emerging KGs. In this paper, we propose KG-S2S, a Seq2Seq generative framework that could tackle different verbalizable graph structures by unifying the representation of KG facts into “flat” text, regardless of their original form. To remedy the KG structure information loss from the “flat” text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S. Experiments on five benchmarks show that KG-S2S outperforms many competitive baselines, setting new state-of-the-art performance. Finally, we analyze KG-S2S’s ability on the different relations and the Non-entity Generations.

With the development of blockchain and communication techniques, the Metaverse is considered as a promising next-generation Internet paradigm, which enables the connection between reality and the virtual world. The key to rendering a virtual world is to provide users with immersive experiences and virtual avatars, which is based on virtual reality (VR) technology and high data transmission rate. However, current VR devices require intensive computation and communication, and users suffer from high delay while using wireless VR devices. To build the connection between reality and the virtual world with current technologies, mobile augmented reality (MAR) is a feasible alternative solution due to its cheaper communication and computation cost. This paper proposes an MAR-based connection model for the Metaverse, and proposes a communication resources allocation algorithm based on outer approximation (OA) to achieve the best utility. Simulation results show that our proposed algorithm is able to provide users with basic MAR services for the Metaverse, and outperforms the benchmark greedy algorithm.

Reputation/trust-based blockchain systems have attracted considerable research interests for better integrating Internet of Things with blockchain in terms of throughput, scalability, energy efficiency, and incentive aspects. However, most existing works only consider static adversaries. Hence, they are vulnerable to slowly adaptive attackers, who can target validators with high reputation value to severely degrade the system performance. Therefore, we introduce$\textsf{zkRep}$, a privacy-preserving scheme tailored for reputation-based blockchains. Our basic idea is to hide both the identity and reputation of the validators by periodically changing the identity and reputation commitments (i.e., aliases), which makes it much more difficult for slowly adaptive attackers to identify validators with high reputation value. To realize this idea, we utilize privacy-preserving Pedersen-commitment-based reputation updating and leader election schemes that operate on concealed reputations within an epoch. We also introduce a privacy-preserving identity update protocol that changes the identity and time-window-based cumulative reputation commitments during each epoch transition. We have implemented and evaluated$\textsf{zkRep}$on the Amazon Web Service. The experimental results and analysis show that$\textsf{zkRep}$achieves great privacy-preserving features against slowly adaptive attacks with little overhead.

Internet of Vehicles (IoV), a special form of Internet of Things (IoT), is an important enabler of intelligent transportation system, which is one of the most strategic applications in smart city initiatives. In order to achieve its intended functionalities, IoV requires anytime anywhere connectivity, which cannot be satisfied by traditional networking technologies. Space–air–ground-integrated network (SAGIN) is widely believed to be an ideal infrastructure for connecting IoV. In this article, we present an approach for understanding the security issues of complex IoT systems, and propose a security reference architecture for assessing security risks and addressing the security requirements. Specifically, we propose an activity-network-things (ANT)-centric security reference architecture, which is based on the three architectural perspectives in studying IoT systems, namely, device, Internet, and semantic. We discuss the limitations of existing IoT system architecture models, which are mainly evolved from the enterprise system architecture with some adaptation to the inherent features of IoT systems. Our approach can help manage the security risks by focusing on the critical activities performed in different microperimeters within an IoT system. The proposed architecture includes an organized process to understand the security requirements and select specific parameters for tailored security controls that are commensurate with organization-specific and application-specific security impacts of IoT. Our architecture is flexible enough to cater for any IoT application, and hence, can be easily applied to the case of SAGIN-enabled IoV.

The Internet of Vehicles (IoV) was proposed as an approach to enable intelligent traffic management and enhance road safety. In order to achieve the intended objective of improving road safety, vehicles are required to constantly broadcast messages to the traffic management infrastructure as well as to other vehicles in the vicinity. Cybersecurity protection of the IoV system is critical as security attacks on IoV and safety-related messages could be life threatening. In this connection, it is essential to ensure the authenticity of IoV messages. Whereas, from the angle of privacy protection, it is undesirable to directly authenticate the identities of vehicles that send the IoV messages. To cope with these conflicting requirements, researchers proposed the notion of conditional anonymous authentication, which aims to authenticate message senders anonymously. When necessary, a trusted third party, named tracer, will be allowed to reveal the true identities of malicious vehicles who sent fake messages. However, existing security techniques, including pseudonyms and group signatures typically assume that the tracer is trusted. This assumption may not be desirable in situations when a curious tracer may reveal the identities of honest vehicles in the IoV system. To address this challenge, this article proposes a privacy-preserving authentication scheme with abuse-resistant tracing. Compared with existing conditional anonymous authentication schemes, our scheme prevents a single tracer from revealing the identity of vehicles. Besides, the tracing key is generated in a distributed manner, and hence no single authority in the system can reveal the true identity of a vehicle.

With the transmission and sharing of data in the Internet of Things (IoT), while bringing development to life and the economy, it also inevitably threatens the data copyright protection and authentication. Digital watermarking technology can provide an effective solution for copyright protection by embedding the watermark in the data to prove the copyright attribution. The existing methods of digital watermarking in IoT mainly target multimedia, without considering the copyright authentication in database data. Unlike multimedia information, the database does not focus on the subjective visual perception when using the data, but rather on the potential values unlocked from the data through algorithms such as data mining. Therefore, we propose a new database watermarking algorithm based on decision tree shift correction (DTSC), considering the data copyright authentication and usability when applying for data mining algorithm. The algorithm adjusts the watermarked data by the DTSC method and makes the watermarked decision tree identical to the original in the iteration process. It solves the problem of database data copyright authentication in IoT and ensures the usability of the data when used for decision tree model construction. From the simulation results, it can be seen that the proposed method ensures the usability of the data for the classification and regression tree decision tree algorithm while embedding the watermark in the database data, and the data distortion of the proposed method does not differ from that of the traditional watermarking algorithm.

Face presentation attack detection (PAD) has been extensively studied by research communities to enhance the security of face recognition systems. Although existing methods have achieved good performance on testing data with similar distribution as the training data, their performance degrades severely in application scenarios with data of unseen distributions. In situations where the training and testing data are drawn from different domains, a typical approach is to apply domain adaptation techniques to improve face PAD performance with the help of target domain data. However, it has always been a non-trivial challenge to collect sufficient data samples in the target domain, especially for attack samples. This paper introduces a teacher-student framework to improve the cross-domain performance of face PAD with one-class domain adaptation. In addition to the source domain data, the framework utilizes only a few genuine face samples of the target domain. Under this framework, a teacher network is trained with source domain samples to provide discriminative feature representations for face PAD. Student networks are trained to mimic the teacher network and learn similar representations for genuine face samples of the target domain. In the test phase, the similarity score between the representations of the teacher and student networks is used to distinguish attacks from genuine ones. To evaluate the proposed framework under one-class domain adaptation settings, we devised two new protocols and conducted extensive experiments. The experimental results show that our method outperforms baselines under one-class domain adaptation settings and even state-of-the-art methods with unsupervised domain adaptation.

Privacy-preserving data analysis is an emerging area that addresses the dilemma of performing data analysis on user data while protecting users’ privacy. In this paper, we consider the problem of constructing privacy-preservingK-means clustering protocol for data analysis that provides local privacy to users’ data. To enable a desirable degree of local privacy guarantee while maintaining high accuracy of the clustering, we adopt a generalized differential privacy definition,dχ-privacy, which quantifies the distinguishability level based on the distance between data records defined by the distance functiondχ. In our work, we consider the space of data points as a metric space imbued with Euclidean distance and propose a bounded perturbation mechanism (BPM) with bounded sampling space of the perturbed data points, which is formally shown to achievedχ-privacy. BPM perturbs the data as a whole instead of treating each dimension independently, which is desirable since the privacy budget is no longer required to be split among different dimensions. Bounded output space also means that we will not get into the case where the report or the statistical result is so far out of the data domain that it is hard to interpret. Furthermore, it can also help in limiting the amount of bandwidth needed to send such report to the server. The design of BPM is based on a probability density function which decreases exponentially as the Euclidean distance with respect to the true value grows. It is also designed with the aim of ensuring that BPM produces perturbed data that provides the claimed privacy guarantee while ensuring high utility response. To guarantee the efficiency of the perturbation method, we propose an efficient algorithm to sample from the proposed distribution and apply BPM to the design ofdχ-privateK-means clustering algorithms. Lastly, we analyse the privacy and utility guarantee provided by the proposed method and provide its experimental results.

Crowdsourcing plays an essential role in the Internet of Things (IoT) for data collection, where a group of workers is equipped with Internet-connected geolocated devices to collect sensor data for marketing or research purpose. In this article, we consider crowdsourcing these worker's hot travel path. Each worker is required to report his real-time location information, which is sensitive and has to be protected. Encryption-based methods are the most direct way to protect the location, but not suitable for resource-limited devices. Besides, local differential privacy is a strong privacy concept and has been deployed in many software systems. However, the local differential privacy technology needs a large number of participants to ensure the accuracy of the estimation, which is not always the case for crowdsourcing. To solve this problem, we proposed a trie-based iterative statistic method, which combines additive secret sharing and local differential privacy technologies. The proposed method has excellent performance even with a limited number of participants without the need of complex computation. Specifically, the proposed method contains three main components: iterative statistics, adaptive sampling, and secure reporting. We theoretically analyze the effectiveness of the proposed method and perform extensive experiments to show that the proposed method not only provides a strict privacy guarantee, but also significantly improves the performance from the previous existing solutions.

This paper investigates the problem of distributed resource management in two-tier heterogeneous networks, where each cell selects its joint device association, spectrum allocation, and power allocation strategy based only on locally-observed information without any central controller. As the optimization problem with devices’ quality-of-service (QoS) constraints is non-convex and NP-hard, we model it as a Markov decision process (MDP). Considering the fact that the network is highly complex with large state and action spaces, a multi-agent dueling deep-Q network-based algorithm combined with distributed coordinated learning is proposed to effectively learn the optimized intelligent resource management policy, where the algorithm adopts dueling deep network to learn the action-value distribution by estimating both the state-value and action advantage functions. Under the distributed coordinated learning manner and dueling architecture, the learning algorithm can rapidly converge to the optimized policy. Simulation results demonstrate that the proposed distributed coordinated learning algorithm outperforms other existing learning algorithms in terms of learning efficiency, network data rate, and QoS satisfaction probability.

This paper investigates the problem of distributed resource management (i.e., joint device association, spectrum allocation, and power allocation) in two-tier heterogeneous networks without any central controller. Considering the fact that the network is highly complex with large state and action spaces, a multi-agent dueling deep-Q network-based algorithm combined with distributed coordinated learning is proposed to effectively learn the optimized intelligent resource management policy, where the algorithm adopts dueling deep network to learn the action-value distribution by estimating both the state-value and action advantage functions. Under the distributed coordinated learning manner and dueling architecture, the learning algorithm can rapidly converge to the optimized policy. Simulation results demonstrate that the proposed distributed coordinated learning algorithm outperforms other existing learning algorithms in terms of learning efficiency, network data rate, and QoS satisfaction probability.

Internet of Vehicles (IoV) is an emerging concept that is believed to help realize the vision of intelligent transportation systems (ITSs). IoV has become an important research area of impactful applications in recent years due to the rapid advancements in vehicular technologies, high throughput satellite communication, the Internet of Things, and cyber-physical systems. IoV enables the integration of smart vehicles with the Internet and system components attributing to their environments, such as public infrastructures, sensors, computing nodes, pedestrians, and other vehicles. By allowing the development of a common information exchange platform between vehicles and heterogeneous vehicular networks, this integration aims to create a better environment and public space for the people as well as to enhance safety for all road users. Being a participatory data exchange and storage, the underlying information exchange platform of IoV needs to be secure, transparent, and immutable in order to achieve the intended objectives of ITS. In this connection, the adoption of blockchain as a system platform for supporting the information exchange needs of IoV has been explored. Due to their decentralized and immutable nature, IoV applications enabled by blockchain are believed to have a number of desirable properties, such as decentralization, security, transparency, immutability, and automation. In this article, we present a contemporary survey on the latest advancement in blockchain for IoV. Particularly, we highlight the different application scenarios of IoV after carefully reviewing the recent literature. We also investigate several key challenges where blockchain is applied in IoV. Furthermore, we present the future opportunities and explore further research directions of IoV as a key enabler of ITS.

The concept of smart grid has been introduced as a new vision of the conventional power grid to figure out an efficient way of integrating green and renewable energy technologies. In this way, Internet-connected smart grid, also called energy Internet, is also emerging as an innovative approach to ensure the energy from anywhere at any time. The ultimate goal of these developments is to build a sustainable society. However, integrating and coordinating a large number of growing connections can be a challenging issue for the traditional centralized grid system. Consequently, the smart grid is undergoing a transformation to the decentralized topology from its centralized form. On the other hand, blockchain has some excellent features which make it a promising application for the smart grid paradigm. In this article, we aim to provide a comprehensive survey on the application of blockchain in smart grid. As such, we identify the significant security challenges of smart grid scenarios that can be addressed by blockchain. Then, we present a number of blockchain-based recent research works presented in different literature addressing security issues in the area of smart grid. We also summarize several related practical projects, trials, and products that have emerged recently. Finally, we discuss essential research challenges and future directions of applying blockchain to smart grid security issues.

An increasing amount of users' sensitive information is now being collected for analytics purposes. Differential privacy has been widely studied in the literature to protect the privacy of users' information. The privacy parameter bounds the information about the data set leaked by the noisy output. Oftentimes, a data set needs to be used for answering multiple queries, so the level of privacy protection may degrade as more queries are answered. Thus, it is crucial to keep track of privacy budget spending, which should not exceed the given limit of privacy budget. Moreover, if a query has been answered before and is asked again on the same data set, we may reuse the previous noisy response for the current query to save the privacy cost. In view of the above, we design an algorithm to reuse previous noisy responses if the same query is asked repeatedly. In particular, considering that different requests of the same query may have different privacy requirements, our algorithm can set the optimal reuse fraction of the old noisy response and add new noise to minimize the accumulated privacy cost. Furthermore, we design and implement a blockchain-based system for tracking and saving differential-privacy cost. As a result, the owner of the data set will have full knowledge about how the data set has been used and be confident that no new privacy cost will be incurred for answering queries once the specified privacy budget is exhausted.

The Internet of Vehicles (IoV) is a promising branch of the Internet of Things. IoV simulates a large variety of crowdsourcing applications, such as Waze, Uber, and Amazon Mechanical Turk, etc. Users of these applications report the real-time traffic information to the cloud server which trains a machine learning model based on traffic information reported by users for intelligent traffic management. However, crowdsourcing application owners can easily infer users' location information, traffic information, motor vehicle information, environmental information, etc., which raises severe sensitive personal information privacy concerns of the users. In addition, as the number of vehicles increases, the frequent communication between vehicles and the cloud server incurs unexpected amount of communication cost. To avoid the privacy threat and reduce the communication cost, in this article, we propose to integrate federated learning and local differential privacy (LDP) to facilitate the crowdsourcing applications to achieve the machine learning model. Specifically, we propose four LDP mechanisms to perturb gradients generated by vehicles. The proposed Three-Outputs mechanism introduces three different output possibilities to deliver a high accuracy when the privacy budget is small. The output possibilities of Three-Outputs can be encoded with two bits to reduce the communication cost. Besides, to maximize the performance when the privacy budget is large, an optimal piecewise mechanism (PM-OPT) is proposed. We further propose a suboptimal mechanism (PM-SUB) with a simple formula and comparable utility to PM-OPT. Then, we build a novel hybrid mechanism by combining Three-Outputs and PM-SUB. Finally, an LDP-FedSGD algorithm is proposed to coordinate the cloud server and vehicles to train the model collaboratively. Extensive experimental results on real-world data sets validate that our proposed algorithms are capable of protecting privacy while guaranteeing utility.

Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, machine learning (ML) model training, and wireless communications. However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is impractical to send raw data of devices to UAV servers for model training. Moreover, due to the dynamic channel condition and heterogeneous computing capacity of devices in UAV-enabled networks, the reliability and efficiency of data sharing require to be further improved. In this paper, we develop an asynchronous federated learning (AFL) framework for multi-UAV-enabled networks, which can provide asynchronous distributed computing by enabling model training locally without transmitting raw sensitive data to UAV servers. The device selection strategy is also introduced into the AFL framework to keep the low-quality devices from affecting the learning efficiency and accuracy. Moreover, we propose an asynchronous advantage actor-critic (A3C) based joint device selection, UAVs placement, and resource management algorithm to enhance the federated convergence speed and accuracy. Simulation results demonstrate that our proposed framework and algorithm achieve higher learning accuracy and faster federated execution time compared to other existing solutions.

Reconfigurable intelligent surface (RIS), a recently introduced technology for future wireless communication systems, enhances the spectral and energy efficiency by intelligently adjusting the propagation conditions between base stations (BSs) and mobile equipments (MEs). An RIS consists of many low-cost passive reflecting elements that are optimized to improve the quality of the received signal. In this paper, we study the problem of power control at the BS and RIS optimization for application to physical-layer broadcasting. Our goal is to minimize the transmit power at the BS by jointly designing the transmit beamforming at the BS and the phase shifts of the passive elements at the RIS. Furthermore, to help validate the proposed optimization methods, we derive lower bounds to quantify the average transmit power at the BS as a function of the number of MEs, the number of RIS elements, and the number of antennas at the BS. The simulation results demonstrate that the average transmit power at the BS is close to the lower bound in an RIS-aided system, and is significantly lower than the average transmit power in conventional schemes without an RIS.

Security of (semi)-autonomous vehicles is a growing concern, first, due to the increased exposure of the functionality to potential attackers; second, due to the reliance of functionalities on diverse (semi)-autonomous systems; third, due to the interaction of a single-vehicle with myriads of other smart systems in urban traffic infrastructure. Beyond these technical issues, we argue that the security-by-design principle for smart and complex autonomous systems, such as an Autonomous Vehicle (AV) is poorly understood and rarely practiced. Unlike traditional IT systems, where the risk mitigation techniques and adversarial models are well studied and developed with security design principles such as security perimeter and defense-in-depth, the lack of such a framework for connected autonomous systems is plaguing the design and implementation of a secure AV. We attempt to identify the core issues of securing an AV. This is done methodically by developing a security-by-design framework for AV from the first principles. Subsequently, the technical challenges for AV security are identified.

The personalized Web service recommendation based on Quality of Service (QoS) is gaining increasing popularity due to its promising ability to help users find high quality services. Studies suggest that it is beneficial to use Collaborative Filtering (CF)-based techniques to facilitate Web service recommendations which can achieve high accuracy in predicting the QoS for unobserved Web services. With the QoS, location of users and Web services has been another significant factor in predicting the QoS values. The more factors that are available to the service providers, the more accurate predictions can be generated. However these factors are privacy sensitive and therefore it is risky to disclose them to any third party service provider. To address this challenge, in this paper we develop a privacy preserving protocol to predict missing QoS values and thereby providing Web service recommendations based on past QoS experiences and locations of users. Our protocol is able to achieve user privacy by means of encrypting the QoS and location as well as to select suitable Web services for users without disclosing any private information. We conduct extensive experimental analysis on publicly available data sets and prove that our method is both secure and practical.

In this paper, we study an intelligent reflecting surface (IRS)-aided wireless secure communication system for physical layer security, where an IRS is deployed to adjust its reflecting elements to secure the communication of multiple legitimate users in the presence of multiple eavesdroppers. Aiming to improve the system secrecy rate, a design problem for jointly optimizing the base station (BS)'s beamforming and the IRS's reflecting beamforming is formulated considering different quality of service (QoS) requirements and time-varying channel conditions. As the system is highly dynamic and complex, a novel deep reinforcement learning (DRL)-based secure beamforming approach is firstly proposed to achieve the optimal beamforming policy against eavesdroppers in dynamic environments. Simulation results demonstrate that the proposed deep learning based secure beamforming approach can significantly improve the system secrecy performance compared with other approaches.

Presentation attack is one of the main threats to face verification systems and attracts great attention of research community. Recent methods achieve great success in intra-database test. However, the problem is more complex in practical scenario as the type of attack could be unseen to system designers. In this paper, we formulate the face presentation attack detection task under an open-set setting and address with our proposed deep anomaly detection based method. The training process is end-to-end supervised by a novel hypersphere loss function and the decision making is directly based on the learned feature representation. We conduct extensive experiments on multiple prevailing databases and evaluate our implemented models by using various metrics. The results show our proposed method is effective against unseen types of attacks and superior to latest state-of-the-art.

Formal analyses of blockchain protocols have received much attention recently. Consistency results of Nakamoto's blockchain protocol are often expressed in a quantity c, which denotes the expected number of network delays before some block is mined. With μ (resp., ν) denoting the fraction of computational power controlled by benign miners (resp., the adversary), where μ+ν =1, we prove for the first time that to ensure the consistency property of Nakamoto's blockchain protocol in an asynchronous network, it suffices to have c to be just slightly greater than 2μ/(ln(μ/ν)). Such a result is both neater and stronger than existing ones. In the proof, we formulate novel Markov chains which characterize the numbers of mined blocks in different rounds.

The evolution of Internet of Things (IoT) devices and their adoption in new generation intelligent systems has generated a huge demand for wireless bandwidth. This bandwidth problem is further exacerbated by another characteristics of IoT applications, i.e., IoT devices are usually deployed in massive number, thus leading to an awkward scenario that many bandwidth-hungry devices are chasing after the very limited wireless bandwidth within a small geographic area. As such, cognitive radio has received much attention of the research community as an important means for addressing the bandwidth needs of IoT applications. When enabling IoT devices with cognitive functionalities including spectrum sensing, dynamic spectrum accessing, circumstantial perceiving, and self-learning, one will also need to fully study other critical issues such as standardization, privacy protection, and heterogeneous coexistence. In this article, we investigate the structural frameworks and potential applications of cognitive IoT. We further discuss the spectrum-based functionalities and heterogeneity for cognitive IoT. Security and privacy issues involved in cognitive IoT are also investigated. Finally, we present the key challenges and future direction of research on cognitive-radio-based IoT networks.

In this paper, we consider a scenario where a user queries a user profile database, maintained by a social networking service provider, to identify users whose profiles match the profile specified by the querying user. A typical example of this application is online dating. Most recently, an online dating website, Ashley Madison, was hacked, which resulted in a disclosure of a large number of dating user profiles. This data breach has urged researchers to explore practical privacy protection for user profiles in a social network. In this paper, we propose a privacy-preserving solution for profile matching in social networks by using multiple servers. Our solution is built on homomorphic encryption and allows a user to find out matching users with the help of multiple servers without revealing to anyone the query and the queried user profiles in clear. Our solution achieves user profile privacy and user query privacy as long as at least one of the multiple servers is honest. Our experiments demonstrate that our solution is practical.

In this paper, we consider a scenario where a bitcoin liquidity provider sells bitcoins to clients. When a client pays for a bitcoin online, the provider is able to link the client's payment information to the bitcoin sold to that client. To address the privacy concerns of clients, we require that the bitcoin provider cannot tell the relationship between the real identities of clients and the sold bitcoins in the blockchain. This requirement can be effectively achieved by using blind signatures. However, existing blind signature schemes are incompatible with the Elliptic Curve Digital Signature Algorithm (ECDSA) which is used by most of the existing bitcoin protocol, thus cannot be applied directly in Bitcoin. In this paper, we propose a new blind signature scheme that allows generating a blind signature compatible with the standard ECDSA. Afterwards, we make use of the new scheme to achieve bitcoin transaction anonymity. The new scheme is built on a variant of the Paillier cryptosystem and its homomorphic properties. As long as the modified Paillier cryptosystem is semantically secure, the new blind signature scheme has blindness and unforgeability.

Understanding how people interact and exchange messages on social networks is significant for managing online contents and making predictions of future behaviors. Most existing research on the communication characteristics simply focuses on the user involvement. The current work largely neglects the content changes that imply how wide and deep the discussion in a topic goes, and to what degree people set forth their own views with the additional information supplemented. We are highly motivated to propose a theoretical framework to target those issues. In this paper, we define the communication modality constructs, and classify topics based on three dimensions: user involvement, information flow depth, and topic inter-relations, which substantially extend the traditional focus in user interaction analysis. The communication modality constructs comprise of (i) topic dialogicity, (ii) discussion intensiveness, and (iii) discussion extensibility. We introduce a quantitative model based on the topology of information flow graph, and use the information addition as well as the emotion attachment along the path to measure the pattern divergence between topic groups. Our model is empirically validated by using 78 million tweets, and experiments on Twitter demonstrate our contributions.

Spatio-temporal monitoring of the Internet of Things (IoT) has enabled the development and proliferation of third-party computing services by extensively exploiting the massive amount of sensing data. In particular, continuously generated data stream are monitored in real-time and exploited to facilitate people's daily lives, such as traffic monitoring and epidemic prevention. In its simplest way of deployment, the direct publishing of various streams could seriously compromise the privacy of participating users. Hence, a more sophisticated scheme is needed to regulate the privately publishing of data streams, which may possibly require control to be applied dynamically. However, most existing solutions are non-adaptive to dynamic changes of the streams due to constraints of predefined parameters, thus are vulnerable to low data utility. In this paper, we present AdaPub, a data-adaptive framework for infinite multidimensional stream real-time publishing with ω-event differential privacy while ensuring high data utility. Without predefining the parameters, AdaPub could learn and update the parameters that reflect the spatio-temporal correlations of the stream in a data-adaptive manner. Specifically, we propose two modules DimParti and AdaCluster which are seamlessly incorporated into AdaPub to simultaneously learn dimension correlations and time correlations in a data-adaptive way, thus greatly improving the data utility of the sanitized streams. Extensive experiments on real-world datasets demonstrate that our solution substantially outperforms state-of-the-art solutions with much lower errors while achieving strong privacy guarantees.

The availability of massive social media data has enabled the prediction of people’s future behavioral trends at an unprecedented large scale. Information cascades study on Twitter has been an integral part of behavior analysis. A number of methods based on the transactional features (such as keyword frequency) and the semantic features (such as sentiment) have been proposed to predict the future cascading trends. However, an in-depth understanding of the pros and cons of semantic and transactional models is lacking. This paper conducts a comparative study of both approaches in predicting information diffusion with three mechanisms: retweet cascade, url cascade, and hashtag cascade. Experiments on Twitter data show that the semantic model outperforms the transactional model, if the exterior pattern is less directly observable (i.e. hashtag cascade). When it becomes more directly observable (i.e. retweet and url cascades), the semantic method yet delivers approximate accuracy (i.e. url cascade) or even worse accuracy (i.e. retweet cascade). Further, we demonstrate that the transactional and semantic models are not independent, and the performance gets greatly enhanced when combining both.

IoT devices for video sensing need to operate within the constraints of limited bandwidth and low computing capabilities. To that effect, Compressive Sensing (CS) emerged as a prominent technique for balancing the quality of images/video and the computing/communication overheads. For CS of video data, the Block-based CS (BCS) is typically used due to low complexity. However, while CS reduces the number of samples to be transmitted, the bit-width of each sample increases due to the linear algebraic operations involved in CS, thus making CS less attractive in its pure and straightforward form. To further optimize the use of CS in IoT devices for video sensing, we explore the use of μ-law quantization technique due to its low hardware implementation overhead. We designed and implemented a complete CS platform with the integration of μ-law quantization, and studied the image quality at different compression ratios. The results show that the proposed quantization technique requires only up to 40 additional LUTs compared to the baseline algorithm, while achieving an additional compression of up to 280% in the best case.

In recent years, Industrial Internet of Things (IIoT) has attracted growing attention from both academia and industry. Meanwhile, when traditional wireless sensor networks are applied to complex industrial field with high requirements for real time and robustness, how to design an efficient and practical cross-layer transmission mechanism needs to be fully investigated. In this paper, we propose a Q-learning-based dynamic spectrum access method for IIoT by introducing cognitive self-learning technical solution to solve the difficulty of distributed and ordered self-accessing for unlicensed terminals. We first devise a simplified MAC access protocol for unlicensed users to use single available channel. Then, a Q-learning-based multi-channels access scheme is raised for the unlicensed users migrating to other lower cells. The channel with most Q value will be considered to be selected. Every mobile terminals store and update their own channel lists due to distributed network mode and non-perfect sensing ability. Numerical results are provided to evaluate the performances of our proposed method on dynamic spectrum access in IIoT. Our proposed method outperforms the traditional simplified accessing methods without self-learning capability on channel usage rate and conflict probability.

Wireless sensors and actuators connected by the Internet-of-Things (IoT) are central to the design of advanced cyber-physical systems (CPSs). In such complex, heterogeneous systems, communication links must meet stringent requirements on throughput, latency, and range, while adhering to tight energy budget and providing high levels of security. In this paper, we first summarize wireless communication principles from the perspective of the connectivity needs of IoT and CPS. Based on these principles, we then review the most relevant wireless communication standards before focusing on the key security issues and features of such systems. In particular, the gap between the security features in the communication standards used in CPSs and IoT and their actual vulnerabilities are pointed out with practical examples and recent attacks. We emphasize the need for a more in-depth study of the security issues across all the protocol layers, including both logical layer security and physical layer security.

With the rapid development of modern satellite communications, broadband satellite services are experiencing a period of remarkable growth in both the number of users and the available bandwidth. More efficient spectrum management schemes require deeper investigation in order to meet the ever-increasing demand for broadband spectrum. In this paper, we propose a band allocation method for multibeam satellite systems by introducing a market-driven pricing mechanism. Instead of adopting static and fixed band selling, we consider a satellite network operator that utilizes the mode of price bargaining to trade the unused band with terrestrial network operators. By applying market-based mechanism to support satellite spectrum allocation, higher spectrum efficiency can be attained in order for satellite systems to meet the increasing demands for satellite bandwidth at an affordable cost. Besides, for the one-to-many bargaining case without terrestrial operator involved in, a differential spectrum pricing solution is devised to address heterogeneous users' spectrum preferences. In a typical price bargaining model, market participants (i.e., terrestrial network operators) are assumed to know exactly their needs dynamically, which is hard to achieve in near real-time; thus, our approach approximates it with a sub-optimal estimation on the network operators' benefit threshold. To be specific, we obtain the optimal pricing at every round of bargaining by predicting the overall benefits of terrestrial network operators and reaching the Nash equilibrium. Essential discussions and proofs for the pricing rationality are provided. Numerical results are given to evaluate the impact of the pricing scheme on the profits of satellite systems.

Content caching is a promising approach to enhancing bandwidth utilization and minimizing delivery delay for new‐generation Internet applications. The design of content caching is based on the principles that popular contents are cached at appropriate network edges in order to reduce transmission delay and avoid backhaul bottleneck. In this paper, we propose a cooperative caching replacement and efficiency optimization scheme for IP‐based wireless networks. Wireless edges are designed to establish a one‐hop scope of caching information table for caching replacement in cases when there is not enough cache resource available within its own space. During the course, after receiving the caching request, every caching node should determine the weight of the required contents and provide a response according to the availability of its own caching space. Furthermore, to increase the caching efficiency from a practical perspective, we introduce the concept of quality of user experience (QoE) and try to properly allocate the cache resource of the whole networks to better satisfy user demands. Different caching allocation strategies are devised to be adopted to enhance user QoE in various circumstances. Numerical results are further provided to justify the performance improvement of our proposal from various aspects.

The aim of this study is to find more Karatsuba-like formulae for a fixed set of moduli polynomials in GF(2)[x]. To this end, a theoretical framework is established. The authors first generalise the division algorithm, and then present a generalised definition of the remainder of integer division. Finally, a generalised Chinese remainder theorem is used to achieve their initial goal. As a by-product of the generalised remainder of integer division, the authors rediscover Montgomery's N-residue and present a systematic interpretation of definitions of Montgomery's multiplication and addition operations.

The authors describe how a simple way to split input operands allows for fast VLSI implementations of subquadratic GF(2)[x] Karatsuba–Ofman multipliers. The theoretical XOR gate delay of the resulting multipliers is reduced significantly. For example, it is reduced by about 33 and 25% for n = 2t and n = 3t (t > 1), respectively. To the best of our knowledge, this parameter has never been improved since the original Karatsuba–Ofman algorithm was first used to design GF(2n) multipliers in 1990.

The emerging biometric cryptography has gained significant interests for key management and privacy protection, but the previously proposed schemes using set metrics for fingerprints may either be too weak to offer enough security or suffer from the performance limitations. In this paper, a new fuzzy cryptographic technique without use of chaff data, Randomized Dissolvent Template (RDT), is proposed for biometric set modalities. The proposed technique is designed to dissolve the enrolled biometric set into a random secret resource, so as to construct robust secured templates by exploiting at least two resources of randomness. In this way, when one fingerprint is used for multiple applications, each time the additional information leakage by secured templates will not exceed the new introduced random information, so RDT is reusable. We thus provide two novel RDT-based constructions in practice: Fuzzy Reconciler using set difference threshold and Fuzzy Dissolver using set intersection threshold. Security analysis proves the new constructions have enough computational complexity for the required security properties, and implementations on FVC2002DB fingerprint database show that the proposed schemes can bring about better accuracy performance over current Fuzzy Vault and Fuzzy Extractor, thus are more promising for biometric-based security applications.

Biometric authentication and privacy protection are conflicting issues in a practical system. Since biometrics cannot be revoked or canceled if compromised duo to the permanent association with the user, privacy-preserving biometric recognition is desired. However, the recently proposed template protection schemes are not yet sufficiently mature. Specially, the popular noninvertible transform approach will result in an obvious decrease of GAR for a fixed FAR. In this paper, we put forward a novel anonymous fingerprint recognition scheme, Biomapping, as the first approach to integrate the feature extraction, noninvertible transform, and anonymous query as a whole. Biomapping extracts the fingerprint feature utilizing a minutiae-centered region encoding, then performs anonymous enrollment and verification using the noninvertible and discriminable constructions. Experiments on the public domain database show Biomapping can provide better recognition accuracy along with the ability to protect the biometric template, thus becomes a promising solution for privacy trustworthy biometric applications.

This paper proposes an effective data mining technique for finding useful patterns in streaming sequences. At present, typical approaches to this problem are to search for patterns in a fixed-size window sliding through the stream of data being collected. The practical values of such approaches are limited in that, in typical application scenarios, the patterns are emerging and it is difficult, if not impossible, to determine a priori a suitable window size within which useful patterns may exist. It is therefore desirable to devise techniques that can identify useful patterns with arbitrary window sizes. Attempts to this problem are challenging, however, because it requires a highly efficient searching in a substantially bigger solution space. This paper presents a new method which includes firstly a pruning strategy to reduce the search space and secondly a mining strategy that adopts a dynamic index structure to allow efficient discovery of emerging patterns in a streaming sequence. Experimental results on real data and synthetic data show that the proposed method outperforms other existing schemes both in computational efficiency and effectiveness in finding useful patterns.

Keyphrases can be used to facilitate Web users grasping the main topic(s) of a Web page. We present a practical system of automatic keyphrase extraction for Web pages. In this system, a regression model was first trained based on a set of human-labeled documents. Then it was used to extract keyphrases from new pages automatically. This paper makes three contributions. First, the structure information in a Web page was investigated for keyphrase extraction task. Second, the query log data associated with a Web page collected by a search engine server were used to help keyphrase extraction. Third, a method was put forward in this paper in order to evaluate the similarity of phrases.

There is an important query requirement missing for search engines. With the wide variation of domain knowledge and user interest, a user would like to retrieve documents in which one query term is discussed in the context of another. Based on existing query mechanisms, what can be specified at most is the co-occurrence of multiple terms in a query. This is insufficient because the co-occurrence of two terms does not necessarily mean that one is discussed in the context of the other. In this paper we propose the context query for Web searching. A new query operator, called the 'in' operator, is used to specify context inclusion between two terms. Heuristic rules to identify context inclusion are suggested and implementation of the 'in' operator in search engines is proposed. Results show that both the precision and ranking relevance of Web searching are improved significantly.

The relevance of a Web document could be measured not only by its text content, but also by some other factors such as the link connectivity and usage patterns. In previous data fusion researches, the text is the only source to determine the relevance, and only the different runs (e.g. by different retrieval models, different query or document representations) on this same source are combined. It is the purpose of this paper to investigate whether the different sources can be combined to determine the relevance with a better accuracy than any single source. We conducted a preliminary experiment to test its feasibility and effectiveness and a positive result was obtained.

This paper describes a novel concept of agent warehouse. Non-mobile Web agents typically operate from their users' computer and make request for data possibly from a very far location. In addition, much of this data will be irrelevant to the user, thus aggravating the bandwidth scarcity problem of the Internet. With current mobile agent paradigm, many of these problems such as bandwidth reduction and off-line autonomous negotiation are solved. However, this paradigm does have some significant limitations in its common deployment scenarios; system resource consumption, server collaboration, and accumulated agent size along the travelling path, etc. are some typical ones. These limitations are becoming more important when multiple visits to the same server host are required: updating time of host information is nondeterministic and the decision of negotiation is also not simultaneous. In this paper, the intermediate "proxy-like" agent warehouse is proposed to address these issues. The agent warehouse locates near the data sources and supports agent execution, thus allowing agents to operate much closer to these data sources and minimising the effect of discarded search results. In addition, it is able to provide more resources than a normal Web server host does as it is dedicated to cater for agents. More importantly, even if the remote site does not support agent execution, the agent will still be able to complete its task through the warehouse. This changes the typical approach of how agents can be deployed by providing a more generic, flexible system environment for agents to execute.

Mobile agent technology applied into EC is facing many problems. Security should be the first concern. But in large scale multi-agent systems, the most challenging problems encountered are locating and communicating of these autoprocessing agents. Some approaches have used several different methods to solve these problems. But unfortunately, they were not satisfied either for their complexity, poor performance or their lack of applicability. In our approach, we propose a secure group communication solution toward the security, locating and communication problems. We differentiated the ”Agent-Based” Multicast concept from the traditional ”Host-Based” Multicast. We then described the requirements for providing secure group services and introduce the key distribution method. A cryptographic method is complemented for further protect the agents. Finally, we analyzed the security and performance issues and conclude our solution.

A fast algorithm is presented for determining the linear complexity of a sequence with period p/sup n/ over GF (q), where p is an odd prime, and where q is a prime and a primitive root (mod p/sup 2/).

We present a new application of algebraic curves over finite fields to the constructions of universal hash families and unconditionally secure codes. We show that the constructions derived from the Garcia-Stichtenoth curves yield new classes of authentication codes and universal hash families which are substantially better than those previously known.

In this paper we present a binary-tree approach to the construction of all binary duadic codes of length n = pm . We also calculate the number of binary duadic codes of length n = pm , where p ≡ +1 (mod 8) is a prime.

In this correspondence we describe several classes of binary sequences with three-level autocorrelation. Those classes of binary sequences are based on cyclic almost difference sets. Some classes of binary sequences have optimum autocorrelation.

For stream ciphers, we need to generate pseudorandom sequences which are of properties of unpredictability and randomness. A important measure of unpredictability and randomness is the linear complexity profile (l.c.p.) l/sub a/(n) of a sequence a. A sequence a is called almost perfect if the l.c.p. is l/sub a/(n)=n/2+O(1). Based on curves over finite fields, we present a method to construct almost perfect sequences. We also illustrate our construction by explicit examples from the projective line and elliptic curves over the binary field.

Based on curves over finite fields with many rational points, we present two constructions of linear codes from local expansions of functions at a fixed rational point. It turns out that codes from our constructions have the same bound on their parameters as Goppa's (1981) geometry codes. Furthermore, we prove that our second construction is equivalent to Goppa's construction. Finally, an additional construction of linear codes from maximal curves shows that these codes have better parameters than Goppa's geometry codes from maximal curves for a certain interval of parameters.

A generalization of algebraic-geometry codes based on function fields over finite fields with many places of small degree is presented. It turns out that many good linear codes can be obtained from these generalized algebraic-geometry codes. In particular, we calculate some examples of q-ary linear codes for q=2,3, 5. These examples show that many best possible linear codes can be found from our construction.

In the current mobile communication networks, users have to trtistnetwork operators to make correct.charges over the cds they made.There islack of evidence to resolve possible disputti+ over thenurnberofcdls and the duration of each cd.Such a concern may grow when users roam among different network operators.This paper proposes an efficient solution to undeniable b]~ng when a mobile user roams into foreign networks.This is achieved by the combination of digitd signature and hash-chaining techniques.Mobile users need to submit a digitd signature when requesting a cd and release chained h~

We propose a secure auction-like negotiation protocol for agent based Internet trading, which not only retains the agent's mobility and flexibility, but also takes secure measures to prevent attacks from malicious hosts during the negotiation process. The particular features of the proposed protocol are: (1) negotiation for agent based trading is performed through a novel pattern of electronic auction; (2) negotiation results between two hosts are ensured to be valid with their signatures; (3) malicious actions can be detected and the breeder can be dug out by the help of sociological factors; (4) information gathering and negotiation processes are combined together while few communications are needed.

This paper observes the Hong Kong Government's position on Internet issues, and discusses why present computerrelated legislation fails to attain its goal of anti-hacking.The paper gives a Hong Kong perspective to government's effort to curb intrusion of businesses on the Internet.The Internet has grown dramatically in recent years with tens of millions of people having access to it.There are also increases in both varieties and number of businesses operating on the Internet.It is therefore more profitable for serious intruders to break into the global network and obtain illegal access to network resources.The situation will only deteriorate if not handled promptly and in a proper manner.