ABSTRACT The rise in malware attacks on Internet of Things (IoT)‐based Android devices has significantly increased cybersecurity risks. To combat these threats, researchers have introduced machine learning (ML) and deep learning (DL) methods. However, the rapid spread of Android devices across diverse geographic areas has resulted in distributed data, rendering traditional methods suboptimal. Centralizing data not only raises privacy concerns but also introduces overhead and scalability issues. To address these challenges, the research community has developed federated learning (FL)‐based systems for Android malware classification, aiming to balance privacy and scalability without compromising effectiveness. In the standard FL paradigm, federated averaging (FedAvg) converges the local models of all participating clients into a global model in each iteration. A notable limitation of FedAvg, however, is that it does not differentiate between the contributions of individual local models, leading to potential performance degradation if suboptimal local models are included. This research introduces a dynamic weighted federated averaging (DW‐FedAvg) mechanism to overcome these limitations. DW‐FedAvg adjusts the weights of each local model based on its performance at the client level. The efficacy of DW‐FedAvg was evaluated using four benchmark datasets in Android malware classification. Preliminary results demonstrate that the proposed methodology outperforms traditional FedAvg and other state‐of‐the‐art techniques in terms of scalability, privacy preservation, and performance metrics such as accuracy, F1 score, AUC score, and FPR score.

This paper proposes a secure active reconfigurable intelligent surfaces (RIS)-assisted multiple input multiple output integrated sensing, communication, and computation over-theair system. Distributed sensors simultaneously sense targets and transmit private data to an access point (AP) via over-the-air computation, while a passive eavesdropper attempts to intercept. We formulate a joint optimization problem to minimize the AP’s computational mean-squared error (MSE) under constraints on the eavesdropper’s computational MSE, sensing accuracy, and transmit power through the jointly design of transmit beam-forming, aggregation beamforming, and active RIS reflection coefficients. Under perfect wiretap channel state information (CSI), the formulated non-convex problem is decomposed and solved via a penalty-based alternating optimization algorithm, using closed-form aggregation beamformer and successive convex approximation. The framework is extended to imperfect wiretap CSI with norm-bounded uncertainty. By deriving a conservative lower bound on the eavesdropper’s distortion and applying the Generalized S-Procedure, a robust alternating optimization algorithm is developed to solve the reformulated problem. Simulations validate the superiority of the proposed scheme over benchmarks with passive or randomly configured active RIS. Key system parameters, including sensor count, security and sensing accuracy thresholds, are analyzed to provide practical insights.

Privacy inference poses a significant threat to users of online social networks (OSNs). To deal with this issue, a number of privacy-enhancing technologies have been proposed with the goal of achieving a balance between the protection of privacy and the utility of data. Previous studies, however, failed to take into consideration the impact of the interdependency of privacy (IoP), which dictates that privacy decisions made by some users may affect the privacy of some other users. The implication of IoP is that too much privacy may be disclosed when multiple individuals share data with the same data accessor because privacy conflicts resulting from independent privacy decisions would make it possible for adversaries to infer the privacy of the target user. Ideally, cooperation that preserves privacy should allow OSN users to respect each other’s privacy specifications so as to resolve such privacy conflicts caused by independent privacy decisions of individuals. To facilitate the design, we propose a privacy-preserving cooperation framework based on the evolutionary game theory to facilitate such cooperation. Based on the framework, the dynamics of user strategies regarding whether to participate in the cooperation are analyzed and an evolutionary stable state is derived to serve as the basis for incentivizing users to participate in cooperative privacy protection. Experiments based on real OSN data show that the proposed cooperation framework is effective in modeling the behaviors of users and that the proposed incentive allocation method can incentivize users to participate in the cooperation. The proposed cooperation framework can not only helps lower the threat to user privacy resulting from privacy inference by data accessors but also allows OSN service providers to design effective privacy protection policies.

This paper presents the first performance analysis of physical layer downlink secure transmissions in a scalable cell-free massive MIMO (SCF-mMIMO) system. A stochastic geometry approach is used to model the locations of the access points (APs), user equipments (UEs) and eavesdroppers (Eves) as independent homogeneous Poisson point processes (HPPPs). In addition to applying maximum ratio transmission (MRT) to send the confidential messages, null-space artificial noise is also injected for secrecy enhancement. We analytically characterize the secrecy performance in terms of both the outage-based secrecy transmission rate (STR) and the ergodic secrecy rate (ESR), appropriate for slow quasi-static fading channels and fast block-fading channels, respectively. By utilizing moment matching and Gil-Pelaez inversion theorem, we are able to obtain mathematically tractable approximations for the performance metrics. These approximations are shown to have high accuracy as compared to simulation results. Our numerical results reveal useful design insights that cannot be inferred from existing studies. These insights answer important questions such as whether it is best to deploy as many APs each with fewer antennas and to what extent the artificial noise insertion is beneficial.

A scalable cell-free massive MIMO (SCF-mMIMO) system where all user equipments (UEs) and access points (APs) employ finite resolution digital-to-analog converters (DACs) and analog-to-digital converters (ADCs) over correlated Rician fading is presented and analysed in this paper. A closed-form expression for the uplink (UL) spectral efficiency (SE) using maximal-ratio combining (MRC) detection for centralized scheme is first derived. Moreover, a novel low complexity partial MMSE (P-MMSE) detector is proposed, which achieves very similar SE performance and maintains much less computational complexity in comparison with the original partial MMSE (P-MMSE) detector. In addition, a joint algorithm consisting of AP cluster formation, pilot assignment, and power control policy is proposed, which yields much higher SE performance than random pilot assignment and user-group based pilot assignment policies do, and meanwhile improves the quality of service (QoS) fairness for all accessing UEs as compared to the equal power transmit policy.