IEEE journal on selected areas in communications : a publication of the IEEE Communications Society最新文献

Adaptive Learning for IRS-Assisted Wireless Networks: Securing Opportunistic Communications Against Byzantine Eavesdroppers irs辅助无线网络的自适应学习：保护机会主义通信免受拜占庭窃听

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-05 DOI: 10.1109/JSAC.2026.3670779

Amirhossein Taherpour;Abbas Taherpour;Tamer Khattab

{"title":"Adaptive Learning for IRS-Assisted Wireless Networks: Securing Opportunistic Communications Against Byzantine Eavesdroppers","authors":"Amirhossein Taherpour;Abbas Taherpour;Tamer Khattab","doi":"10.1109/JSAC.2026.3670779","DOIUrl":"10.1109/JSAC.2026.3670779","url":null,"abstract":"This article introduces a unified learning framework for Byzantine-resilient spectrum sensing and secure transmission in intelligent reflecting surface (IRS)-assisted networks under channel state information (CSI) uncertainty. The sensing module employs robust Bayesian belief updates with adversary-resistant aggregation and consensus, guaranteeing reliable primary user (PU) detection even when a bounded fraction of users are malicious. Based on the sensing outcome, the transmission module formulates the downlink design as a sum mean-squared error (MSE) minimization problem under transmit-power and signal-leakage constraints, jointly optimizing the base station (BS) precoder, IRS configuration, and user equalizers. For partial or known CSI, we develop a lightweight alternating optimization algorithm with provable sublinear convergence. For unknown CSI, we integrate constrained Bayesian optimization (BO) within a geometry-aware, low-dimensional latent space. Simulations demonstrate that the proposed framework achieves a higher probability of detection at a fixed false-alarm rate under adversarial attacks compared to state-of-the-art schemes. It also yields substantial reductions in user MSE, strong suppression of eavesdropper signal power, and fast convergence. This work provides a practical, resilient solution for coherent sensing–communication coordination in emerging sixth-generation (6G) applications such as vehicular, uncrewed aerial vehicle (UAV), and Internet of Things (IoT) networks.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3926-3948"},"PeriodicalIF":17.2,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421986","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IRS-Aided Secure Sensing for Surveillance Area Coverage: Framework and Algorithm Design 红外光谱辅助监控区域覆盖的安全感知：框架与算法设计

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-05 DOI: 10.1109/JSAC.2026.3671230

Ziheng Zhang;Qingqing Wu;Wen Chen;Yanze Zhu;Ziyuan Zheng;Ying Gao;Qiong Wu

{"title":"IRS-Aided Secure Sensing for Surveillance Area Coverage: Framework and Algorithm Design","authors":"Ziheng Zhang;Qingqing Wu;Wen Chen;Yanze Zhu;Ziyuan Zheng;Ying Gao;Qiong Wu","doi":"10.1109/JSAC.2026.3671230","DOIUrl":"10.1109/JSAC.2026.3671230","url":null,"abstract":"This paper proposes a novel IRS-aided framework for secure sensing, which aims to minimize the worst-case Cramér-Rao bound (WC-CRB) within an entire surveillance area by optimizing the IRS reflecting beamforming, enabling reliable and secure localization of arbitrary and unknown targets. Specifically, we first establish a general IRS-aided localization coverage model and derive the closed-form expression for the CRB of an arbitrary point, which reveals the relationship between the localization error bound and the Fisher information of the angle of arrival (AOA), angle of departure (AOD) and delay. To solve this challenging min-max optimization problem, we design efficient algorithms for different area types. For sector area, we first represent the Fisher information as trigonometric polynomials, then construct the WC-CRB coverage constraint as a non-negativity problem of these polynomials, and finally approximate it as an efficiently solvable semidefinite program (SDP). For the more challenging case of arbitrarily shaped area, we propose a two-tiered solution comprising a low-complexity heuristic algorithm based on geometric approximation and a high-performance detailed design that accurately solves the problem by decomposing the irregular boundary into multiple continuous segments. Numerical simulations validate the superiority of the proposed framework, demonstrating that our designs significantly outperform various benchmark schemes in terms of robustness and performance uniformity. The results show that the framework not only effectively reduces the WC-CRB but also achieves a highly uniform performance coverage across the entire area, providing a reliable and efficient solution for practical localization security applications.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3965-3980"},"PeriodicalIF":17.2,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Precise RF-Vision Fusion UAV Positioning and Identification for 6G Spectrum Security 6G频谱安全的精确射频视觉融合无人机定位与识别

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-05 DOI: 10.1109/JSAC.2026.3671229

Yiyao Wan;Hongtao Liang;Guangyu Wu;Fuhui Zhou;Bruno Crispo;Qihui Wu

{"title":"Precise RF-Vision Fusion UAV Positioning and Identification for 6G Spectrum Security","authors":"Yiyao Wan;Hongtao Liang;Guangyu Wu;Fuhui Zhou;Bruno Crispo;Qihui Wu","doi":"10.1109/JSAC.2026.3671229","DOIUrl":"10.1109/JSAC.2026.3671229","url":null,"abstract":"Precise positioning and identification of unauthorized uncrewed aerial vehicles (UAVs) are of crucial importance for spectrum security and privacy protection in future intelligent networks. Although various single-modality approaches have been investigated, their performance degrades under the sensor-specific noise, resulting in suboptimal performance and robustness. To address these security challenges, we propose a multi-layer radio frequency (RF)-vision fusion framework that synergistically exploits temporal-spectral features of UAV RF signals and spatial-visual information to achieve precise and robust UAV positioning and identification. Moreover, a corresponding unified RF-Vision fusion Network (RFViNet) is designed to exploit the RF-vision cross-modal complementary and semantic synergy. Specifically, by leveraging the novel RF-informed proposal generation, RF-enhanced feature modulation, and RF-guided semantic query modules, the RFViNet effectively exploits the complementary strengths of RF and visual modalities. Furthermore, a practical RF–vision platform is developed to evaluate the performance of our method under various challenging conditions. Experimental results on the real-world dataset demonstrate that the proposed method achieves a competitive 85.8% average precision <inline-formula> <tex-math>$mathrm {AP_{50}}$ </tex-math></inline-formula>, highlighting its potential for enhancing the spectrum security in future intelligent wireless networks.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3949-3964"},"PeriodicalIF":17.2,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Block ModShift: Model Privacy via Dynamic Designed Shifts Block ModShift：通过动态设计的shift来建模隐私

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-04 DOI: 10.1109/JSAC.2026.3670248

Nomaan A. Kherani;Sai Praneeth Karimireddy;Urbashi Mitra

引用次数: 0

Physical Layer Security for Sensing-Communication-Computing-Control Closed Loop: A Systematic Security Perspective 传感-通信-计算-控制闭环的物理层安全：一个系统的安全视角

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-04 DOI: 10.1109/JSAC.2026.3670358

Chengleyang Lei;Wei Feng;Yunfei Chen;Jue Wang;Ning Ge;Shi Jin;Tony Q. S. Quek

{"title":"Physical Layer Security for Sensing-Communication-Computing-Control Closed Loop: A Systematic Security Perspective","authors":"Chengleyang Lei;Wei Feng;Yunfei Chen;Jue Wang;Ning Ge;Shi Jin;Tony Q. S. Quek","doi":"10.1109/JSAC.2026.3670358","DOIUrl":"10.1109/JSAC.2026.3670358","url":null,"abstract":"In industrial automation or emergency rescue, sensors and robots work together with the help of an edge information hub (EIH) containing both communication and computing modules. Typically, the EIH collects the sensing data via the sensor-to-EIH link, processes data and then makes decisions on board before sending commands to the robot via the EIH-to-robot link. This forms a sensing-communication-computing-control (<inline-formula> <tex-math>$textbf {SC}^{3}$ </tex-math></inline-formula>) closed loop. In practice, the inherent openness of wireless links within the closed loop leads to susceptibility to eavesdropping. To this end, this paper refines the conventional physical layer security (PLS) approach with a systematic thinking to safeguard the <inline-formula> <tex-math>$textbf {SC}^{3}$ </tex-math></inline-formula> closed loop. The closed-loop negentropy (CNE), a new metric for the performance of the whole <inline-formula> <tex-math>$textbf {SC}^{3}$ </tex-math></inline-formula> closed loop, is maximized under the closed-loop security constraint. The transmit time, power, bandwidth of both wireless links, and the computing capability, are jointly designed. The optimization problem is non-convex. We leverage the Karush-Kuhn-Tucker (KKT) conditions and the monotonic optimization (MO) theory to derive its globally optimal solution. Simulation results show the performance gain of the proposed systematic approach, and reveal the advantage of exploiting the closed-loop structure-level PLS over the link-level or sum-link-level designs.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3909-3925"},"PeriodicalIF":17.2,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421370","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147361068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Secure Transmission for Cell-Free Symbiotic Radio Communications With Movable Antenna: Continuous and Discrete Positioning Designs 可移动天线无蜂窝共生无线电通信的安全传输：连续和离散定位设计

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-03 DOI: 10.1109/JSAC.2026.3670083

Bin Lyu;Jiayu Guan;Meng Hua;Changsheng You;Tianqi Mao;Abbas Jamalipour

{"title":"Secure Transmission for Cell-Free Symbiotic Radio Communications With Movable Antenna: Continuous and Discrete Positioning Designs","authors":"Bin Lyu;Jiayu Guan;Meng Hua;Changsheng You;Tianqi Mao;Abbas Jamalipour","doi":"10.1109/JSAC.2026.3670083","DOIUrl":"10.1109/JSAC.2026.3670083","url":null,"abstract":"In this paper, we study a movable antenna (MA) empowered secure transmission scheme for reconfigurable intelligent surface (RIS) aided cell-free symbiotic radio (SR) systems. Specifically, the MAs deployed at distributed access points (APs) work collaboratively with the RIS to establish high-quality propagation links for both primary and secondary transmissions, as well as suppressing the risk of eavesdropping on confidential primary information. We consider both continuous and discrete MA position cases and maximize the secrecy rate of primary transmission under the secondary transmission constraints, respectively. For the continuous position case, we propose a two-layer iterative optimization method based on differential evolution with one-in-one representation (DEO), to find a high-quality solution with relatively moderate computational complexity. For the discrete position case, we first extend the DEO based iterative framework by introducing the mapping and determination operations to handle the characteristic of discrete MA positions. To further reduce the computational complexity, we then design a single-layer iterative framework to solve all variables alternatively. In particular, we develop an efficient strategy to derive the sub-optimal solution for the discrete MA positions, superseding the DEO-based method. Numerical results validate the effectiveness of the proposed MA empowered secure transmission scheme along with its optimization algorithms.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3878-3893"},"PeriodicalIF":17.2,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147350411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Jamming Identification With Differential Transformer for Low-Altitude Wireless Networks 低空无线网络差分变压器干扰识别

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-02 DOI: 10.1109/JSAC.2026.3669137

Pengyu Wang;Zhaocheng Wang;Tianqi Mao;Weijie Yuan;Haijun Zhang;George K. Karagiannidis

{"title":"Jamming Identification With Differential Transformer for Low-Altitude Wireless Networks","authors":"Pengyu Wang;Zhaocheng Wang;Tianqi Mao;Weijie Yuan;Haijun Zhang;George K. Karagiannidis","doi":"10.1109/JSAC.2026.3669137","DOIUrl":"10.1109/JSAC.2026.3669137","url":null,"abstract":"Wireless jamming identification, which detects and classifies electromagnetic jamming from non-cooperative devices, is crucial for emerging low-altitude wireless networks consisting of many drone terminals that are highly susceptible to electromagnetic jamming. However, jamming identification schemes adopting deep learning (DL) are vulnerable to attacks involving carefully crafted adversarial samples, resulting in inevitable robustness degradation. To address this issue, we propose a differential transformer framework for wireless jamming identification. Firstly, we introduce a differential transformer network in order to distinguish jamming signals, which overcomes the attention noise when compared with its traditional counterpart by performing self-attention operations in a differential manner. Secondly, we propose a randomized masking training strategy to improve network robustness, which leverages the patch partitioning mechanism inherent to transformer architectures in order to create parallel feature extraction branches. Each branch operates on a distinct, randomly masked subset of patches, which fundamentally constrains the propagation of adversarial perturbations across the network. Additionally, the ensemble effect generated by fusing predictions from these diverse branches demonstrates superior resilience against adversarial attacks. Finally, we introduce a novel consistent training framework that significantly enhances adversarial robustness through dual-branch regularization. Simulation results demonstrate that our proposed methodology is superior to existing methods in boosting robustness to adversarial samples.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3664-3677"},"PeriodicalIF":17.2,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147350444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MA-Aided Integrated Sensing and Covert Communication Systems ma辅助集成传感和隐蔽通信系统

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-02 DOI: 10.1109/JSAC.2026.3669141

Hanyu Yang;Shiqi Gong;Heng Liu;Tao Yu;Chengwen Xing

{"title":"MA-Aided Integrated Sensing and Covert Communication Systems","authors":"Hanyu Yang;Shiqi Gong;Heng Liu;Tao Yu;Chengwen Xing","doi":"10.1109/JSAC.2026.3669141","DOIUrl":"10.1109/JSAC.2026.3669141","url":null,"abstract":"In contrast to conventional fixed-position antennas (FPAs), movable antennas (MAs) are capable of actively exploiting the spatial channel variations to enhance the performance of wireless systems. In this paper, we investigate a movable antenna (MA) aided integrated sensing and covert communication (ISACC) system, where the MA movable regions are quantized into practical discrete positions. We aim to maximize the covert sum rate by jointly optimizing the BS transmit beamformers, the positions of both BS- and user-side MAs, and the radar receive equalizer, subject to constraints on radar echo signal-to-clutter-plus-noise ratio (SCNR) and covertness. To effectively tackle this problem, an efficient successive convex approximation (SCA) based alternating optimization (AO) algorithm is proposed, where the complicated log-fractional objective function is handled by fractional programming (FP) technique, and the discrete MA position variables are optimized by employing the penalty strategy. To obtain useful insights, we then focus on a simple single-user single-target (SUST) scenario, and demonstrate that the optimal Tx MA positions aim to de-correlate the BS-target and BS-Willie channels, whereas the optimal Tx MA positions can be flexibly chosen. Furthermore, we extend our work into the practical imperfect CSI scenario, in which a conservative approximation of the covertness constraint is derived, based on which the proposed AO algorithm is still applicable after some slight modifications. Numerical results demonstrate the superior performance of our proposed algorithms under both perfect CSI and imperfect CSI.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3690-3704"},"PeriodicalIF":17.2,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147351095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-User Covert ISAC Over Rician Fading 多用户隐蔽ISAC在专家衰落

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-02 DOI: 10.1109/JSAC.2026.3669124

Yujie Wu;Min Sheng;Xiaoqi Qin;Junsheng Mu;Junyu Liu;Chengwen Xing;Nan Zhao

{"title":"Multi-User Covert ISAC Over Rician Fading","authors":"Yujie Wu;Min Sheng;Xiaoqi Qin;Junsheng Mu;Junyu Liu;Chengwen Xing;Nan Zhao","doi":"10.1109/JSAC.2026.3669124","DOIUrl":"10.1109/JSAC.2026.3669124","url":null,"abstract":"Integrated sensing and communication (ISAC) emerges as an advanced technology to improve the spectrum efficiency by sharing the same spectrum for both communication and sensing. However, the open nature and the shared spectrum make the privacy a critical issue. Fortunately, covert communication can tackle this issue and provide an additional privacy protection for ISAC. In this paper, we propose a novel multi-user covert ISAC scheme against collusive wardens. Specifically, a dual-functional transmitter senses the wardens while communicating with multiple legitimate users covertly, where the more practical Rician fading is considered. First, we analyze the global detection performance of collusive wardens, where we employ the moment matching to handle the intractable theoretical analysis and computation introduced by Rician fading. Then, we optimize each warden’s detection threshold to achieve the greatest detection, creating the worst scenario for legitimate communication. Under this threat, we maximize the average covert transmission rate through jointly optimizing the power allocation and beamforming. To solve this non-convex optimization problem, semidefinite relaxation and successive convex approximation are adopted to transform it into a convex problem, and a convergence-guaranteed iteration algorithm is developed to obtain the optimal solutions. Simulation results show the superiority of the proposed multi-user covert ISAC scheme while revealing the inherent trade-off among covertness, sensing, and communication.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3634-3647"},"PeriodicalIF":17.2,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147350428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Privacy-Aware Resource Collaboration for Secure UAV-Assisted Federated Edge Learning Systems 安全无人机辅助联邦边缘学习系统的隐私感知资源协作

IF 17.2

IEEE journal on selected areas in communications : a publication of the IEEE Communications Society Pub Date : 2026-03-02 DOI: 10.1109/JSAC.2026.3669101

Yu Ding;Weidang Lu;Kai Feng;Yuan Gao;Baoquan Ren

{"title":"Privacy-Aware Resource Collaboration for Secure UAV-Assisted Federated Edge Learning Systems","authors":"Yu Ding;Weidang Lu;Kai Feng;Yuan Gao;Baoquan Ren","doi":"10.1109/JSAC.2026.3669101","DOIUrl":"10.1109/JSAC.2026.3669101","url":null,"abstract":"Unmanned aerial vehicle (UAV)-assisted federated edge learning (FEL) has emerged as a promising paradigm for privacy-preserving data processing in resource-constrained environments. However, the reliance on open wireless communication inherently exposes the system to eavesdroppers, who can eavesdrop and exploit shared model updates to reconstruct sensitive data, posing serious threats to the privacy and security. To address this challenge, we propose a privacy-aware UAV-assisted FEL framework that integrates adaptive local differential privacy (DP) into the model upload process, where user-specific noise is injected into local updates to prevent eavesdroppers from reconstructing sensitive data. To further enhance security and privacy performance, an indicator named value of privacy and security (VoPS) is designed to characterize the combined connection between training cost and privacy leakage. Furthermore, limited system resources including bandwidth allocation, user CPU frequency, DP noise scale, and UAV CPU frequency are collaboratively optimized under considering leakage threshold and heterogeneous computing constraints. Then, a deep deterministic policy gradient (DDPG)-based resource collaboration and secure aggregation scheme is proposed to solve the problem, in which the continuous optimization strategy is intelligently generated through the interaction between the agent and the dynamic privacy-aware UAV-assisted FEL system. Simulation results validate the effectiveness of the proposed scheme in enhancing the security and privacy performance of the system.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"44 ","pages":"3678-3689"},"PeriodicalIF":17.2,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147350447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0