Wireless sensing is recognized as a promising technology for next-generation wireless networks, utilizing signals from devices such as Wi-Fi to detect and interpret human information, including movement status and sleep quality. However, the broadcast nature of wireless signals poses significant privacy risks, as unauthorized users may intercept these signals, leading to potential privacy breaches. Given the sensitive personal information embedded in CSI data and the limitations of encryption at the transmission end, conventional privacy protection measures are inadequate. Thus, developing physical layer-based privacy protection technologies for wireless sensing is urgently needed. In this paper, we consider a wireless sensing system model addressing privacy leakage issues and characterize wireless sensing performance as a classification problem. We propose a novel multi-antenna signal processing-based privacy protection strategy. To illustrate the fundamental tradeoff between sensing and privacy protection, we model the wireless sensing process as a communication task based on non-cooperative joint source-channel coding and introduce the concept of a sensing rate region. Our main contribution is the characterization of sensing and privacy protection performance at two key points within the sensing rate region:POS, indicating the minimum achievable sensing rate of an illegitimate receiver constrained by the maximum sensing rate of a legitimate receiver, andPOPP, indicating the maximum sensing rate of a legitimate receiver constrained by the minimum sensing rate of an illegitimate receiver. Based on our analysis, we provide strategies to establish achievable boundaries betweenPOSandPOPP. Moreover, we define the secure sensing rateRPP, indicating the privacy protection performance of the system. Within this framework, we examine several illustrative examples, validated through numerical simulations.

This paper tackles a notable security loophole in tag-based Physical-Layer Authentication (PLA) when faced with cooperative attacks, highlighting its significance due to two main reasons. First, while attackers may only observe the tag amid noise, they can reduce the noise effect through multiple observations. Furthermore, several cooperative attackers can orchestrate more sophisticated attacks, achieving goals beyond the reach of a single attacker. In this paper, we propose an enhanced PLA scheme, designated as the Enhanced Detection of Cooperative Attacks (EDCA) scheme, to counter these cooperative threats. The basic idea of the EDCA scheme involves utilizing a unique noise characteristic induced by replayed signals to identify and thwart cooperative attacks, preventing attackers from accumulating multiple observations of the same tag. We theoretically analyze the proposed scheme over fading channels and derive closed-form expressions for its performance. Implementation and rigorous evaluation of the EDCA scheme are carried out to compare its performance with prior schemes. Simulation results confirm the alignment of theoretical predictions with empirical outcomes. The proposed scheme not only can effectively detect cooperative attacks but also provide a better detection performance.

This paper addresses the critical challenge of securing two-way Time-of-Arrival (ToA) localization in Wireless Sensor Networks (WSNs) against cooperative distance-enlargement attacks. Existing schemes often rely on heuristic test statistics, are limited to specific attack strategies e.g., Amplify and Forward (AF), or require collaboration among multiple anchor nodes, which hinders their effectiveness against sophisticated adversaries and often incurs high communication overhead. We propose two novel detection schemes based on signal characteristics that overcome these limitations, offering both high accuracy and low complexity. The first scheme, termed the Efficient Detection Scheme of Distance-Enlargement Attacks using Log-Likelihood Ratio (EDDEA-LLR), leverages the Neyman-Pearson (NP) lemma to derive an optimal test statistic for scenarios involving AF attacks. Recognizing the limitations of existing schemes and the EDDEA-LLR scheme in countering Decode and Forward (DF) attacks, we introduce the Efficient Detection Scheme of Distance-Enlargement Attacks by Embedding a Secret Tag (EDDEA-EST). This scheme exploits embedded secret tags within the challenge signal to effectively detect DF attacks. Importantly, the proposed schemes do not require collaboration among multiple anchor nodes, eliminating the need for additional communication and featuring low computational complexity. We provide a rigorous theoretical analysis, deriving closed-form expressions for the detection performance of both schemes. Through extensive simulations, we demonstrate the superiority of the proposed schemes over existing methods in terms of detection accuracy, robustness against both AF and DF attacks, and comprehensive performance considering communication overhead.

High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly deployed distributed training modes for recommendation models. Although synchronous AR training is designed to have higher training efficiency, asynchronous PS training would be a better choice for training speed when there are stragglers (slow workers) in the shared cluster, especially under limited computing resources. An ideal way to take full advantage of these two training modes is to switch between them upon the cluster status. However, switching training modes often requires tuning hyper-parameters, which is extremely time- and resource-consuming. We find two obstacles to a tuning-free approach: the different distribution of the gradient values and the stale gradients from the stragglers. This paper proposes Global Batch gradients Aggregation (GBA) over PS, which aggregates and applies gradients with the same global batch size as the synchronous training. A token-control process is implemented to assemble the gradients and decay the gradients with severe staleness. We provide the convergence analysis to reveal that GBA has comparable convergence properties with the synchronous training, and demonstrate the robustness of GBA the recommendation models against the gradient staleness. Experiments on three industrial-scale recommendation tasks show that GBA is an effective tuning-free approach for switching. Compared to the state-of-the-art derived asynchronous training, GBA achieves up to 0.2% improvement on the AUC metric, which is significant for the recommendation models. Meanwhile, under the strained hardware resource, GBA speeds up at least 2.4x compared to synchronous training.