IEEE Transactions on Information Forensics and Security最新文献

{"title":"MOJO: MOtion Pattern Learning and JOint-Based Fine-Grained Mining for Person Re-Identification Based on 4D LiDAR Point Clouds","authors":"Zhiyang Lu;Chenglu Wen;Ming Cheng;Cheng Wang","doi":"10.1109/TIFS.2025.3614500","DOIUrl":"10.1109/TIFS.2025.3614500","url":null,"abstract":"Person Re-identification (ReID) primarily involves the extraction of discriminative representations derived from morphological characteristics, gait patterns, and related attributes. While camera-based Person ReID methods yield notable results, their reliability diminishes in scenarios involving long distances and limited illumination. LiDAR enables the precise acquisition of human point cloud sequences across extended distances, unaffected by variations in lighting or similar factors. Nevertheless, current LiDAR-based Person ReID techniques are limited to static measurements, rendering them susceptible to perturbations from attire variations, occlusions, and similar confounding factors. To address these issues, this manuscript introduces MOJO, which is applied to 4D LiDAR point clouds to extract unique motion patterns specific to individuals. To characterize the motion patterns across two consecutive point cloud frames, MOJO employs optimal transport to compute point-wise motion vectors, thereby enabling the identification of discriminative implicit motion information. To mitigate the attenuation of point cloud density induced by self-occlusion during dynamic motion, MOJO leverages inverse point-wise flow information to integrate forward frames, thereby yielding a comprehensive representation, whilst concurrently ameliorating the effects of heterogeneous density distribution within localized regions of the 4D point cloud data. Additionally, the inherent unordered nature and sparsity of 4D point clouds present significant obstacles to capturing discriminative features. We develop the 3D joint graph to extract scalable fine-grained traits and employ the joint pyramid pooling module to conduct hierarchical spatiotemporal aggregation across the 4D point clouds. Extensive experimental evaluations demonstrate that MOJO achieves state-of-the-art (SOTA) accuracy on the LReID dataset (for LiDAR-based Person Re-identification) and SUSTech1k dataset (for LiDAR-based Gait Recognition) without any pre-training while exhibiting robust performance across various point cloud densities. Our code will be available at <uri>https://github.com/O-VIGIA/MOJO</uri>","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10288-10300"},"PeriodicalIF":8.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lightweight Consensus Mechanism for Large-Scale UAV Networking","authors":"Jingjing Wang, Wei Long, Yizhong Liu, Xin Zhang, Zheng Zhang, Robert H. Deng","doi":"10.1109/tifs.2025.3614501","DOIUrl":"https://doi.org/10.1109/tifs.2025.3614501","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"15 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tensor-Based Joint Hybrid Beamforming and Artificial Noise Design for Secure mmWave MU-MIMO-OFDM Communication Systems","authors":"Dandan Mao, Ze Li, Shuangzhi Li, Wanming Hao, Ning Wang, Wei Xu","doi":"10.1109/tifs.2025.3614447","DOIUrl":"https://doi.org/10.1109/tifs.2025.3614447","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"16 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Precoding Design for Key Generation in Extremely Large-Scale MIMO Near-Field Multi-User Systems","authors":"Tianyu Lu;Liquan Chen;Junqing Zhang;Chen Chen;Trung Q. Duong;Michail Matthaiou","doi":"10.1109/TIFS.2025.3614468","DOIUrl":"10.1109/TIFS.2025.3614468","url":null,"abstract":"This paper develops a physical layer key generation (PLKG) scheme that utilizes artificial randomness in extremely large-scale multiple-input multiple-output (XL-MIMO) near-field multi-user communications to produce shared secret keys for legitimate users. Unlike traditional PLKG schemes, which rely on the variation of wireless channels, this approach introduces noise power via the precoding vectors to create dynamic fluctuations in the line-of-sight (LoS) channels, emulating the rapid changes typically observed in fast-fading channels. This artificial randomness ensures that the user equipment (UEs) can generate secret keys while effectively preventing potential eavesdropping from malicious eavesdroppers. In particular, a novel channel probing protocol is designed, enabling multiple UEs to simultaneously agree on secret keys with the base station (BS) using non-orthogonal pilots, which exploits the difference in the distances and spatial angles of UEs in near-field communications. Secondly, to maximize the secret key rate, an alternating optimization algorithm is proposed, solving two sub-optimization problems. The first sub-problem employs the singular value decomposition (SVD) method to identify the legitimate space and its orthogonal subspace for generating secret keys and preventing eavesdropping attacks, respectively. Subsequently, a Dinkelbach method-based power allocation algorithm is developed to allocate noise power to these two spaces. The second sub-problem uses a water-filling algorithm to implement power allocation among multiple UEs. Finally, to address the issue of precoding noise not being considered in the alternating optimization problem, a deep learning-based method is introduced, which further improves the performance of the scheme. Simulations demonstrate the efficiency of the proposed PLKG scheme over existing schemes.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10572-10587"},"PeriodicalIF":8.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure Beamforming for Integrated Sensing, NOMA Communication, and Over-the-Air Computation Networks","authors":"Changjie Hu;Quanzhong Li;Qi Zhang;Qiang Li","doi":"10.1109/TIFS.2025.3614008","DOIUrl":"https://doi.org/10.1109/TIFS.2025.3614008","url":null,"abstract":"With the rapid evolution of wireless technologies, the deep integration of sensing, communication and computation has heralded a novel and promising paradigm. In this paper, we propose a secure beamforming design framework for integrated sensing, non-orthogonal multiple access (NOMA) communication and over-the-air computation (AirComp) networks, which can provide multi-functional intelligent services for communication-intensive, computation-intensive, delay-sensitive and security-sensitive applications. In the considered network, each dual-functional intelligent device engages in NOMA information transmission and AirComp. Meanwhile, the triple-functional base station conducts target sensing, NOMA signal decoding and data aggregation simultaneously. Our aim is to maximize the sum secrecy rate (SSR) of NOAM devices while ensuring that the quality of service requirements for both sensing and AirComp are met within the transmit power constraints imposed on all nodes. The formulated optimization problem involves coupled variables and logarithmic determinant, thus it is highly non-convex. To solve it, we propose an efficient matrix-extended generalized Lagrangian dual transformation based algorithm with penalty method, which can obtain the Karush-Kuhn-Tucker (KKT) solution to the original problem with low-complexity and convergence guarantee. Additionally, the well-known successive convex approximation based algorithm is also employed to address the formulated SSR maximization problem. However, its computational complexity significantly exceeds that of our proposed algorithm. Finally, extensive experiments demonstrate the performance improvement of our proposal compared with the benchmark approaches.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10315-10331"},"PeriodicalIF":8.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Two-Stage Jamming Detection and Channel Estimation for UAV-Based IoT Systems","authors":"Tasneem Assaf;Mohammad Al-Jarrah;Arafat Al-Dweik;Zhiguo Ding;Emad Alsusa;Anshul Pandey","doi":"10.1109/TIFS.2025.3614004","DOIUrl":"10.1109/TIFS.2025.3614004","url":null,"abstract":"This work proposes an efficient two-stage jamming detection and channel estimation algorithm for orthogonal frequency division multiplexing (OFDM)-based uncrewed aerial vehicles (UAVs) communications. The proposed scheme is designed based on the unique time and frequency domain statistical characteristics of OFDM signals. In the time domain (TD), a likelihood ratio test (LRT)-based decision rule is derived as a function of the inherent correlation between the cyclic prefix (CP) samples and their counterparts in the OFDM symbol. In addition, in the frequency domain (FD), a closed-form joint jamming detection and channel estimation scheme is derived using the maximum a posteriori probability (MAP) principle as a function of the statistics of the received pilots and virtual subcarriers (VSCs) signals, which is then re-expressed using the generalized MAP ratio test (GMAPRT). The system’s complexity is reduced by applying the two stages sequentially, where the possible implementation of the second stage is conditioned on the outcome of the first stage. The performance of the proposed algorithm is evaluated using Monte Carlo simulations, where the results demonstrate its effectiveness compared to the TD-only and FD-only approaches. The results confirm the superior performance of the proposed scheme compared to the cyclostationary feature (CF)-based technique under various operating scenarios.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10449-10464"},"PeriodicalIF":8.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145133821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robustness Matters: Pre-Training Can Enhance the Performance of Encrypted Traffic Analysis","authors":"Luming Yang;Lin Liu;Jun-Jie Huang;Jiangyong Shi;Shaojing Fu;Yongjun Wang;Jinshu Su","doi":"10.1109/TIFS.2025.3613970","DOIUrl":"10.1109/TIFS.2025.3613970","url":null,"abstract":"Models with large-scale parameters and pre-training have been leveraged for encrypted traffic analysis. However, existing researches primarily focused on accuracy, often overlooking the role of large-scale pre-trained parameters in enhancing robustness. While machine learning (ML) and deep learning (DL) models trained from scratch can achieve high accuracy, they exhibit limited robustness. When subjected to network noise in real-world, their identification results can fluctuate significantly, which is unacceptable. Unfortunately, current robustness evaluation methods neglect samples diversity and employ unreasonable noise settings. This field still lacks a reasonable quantitative description of models robustness. In this paper, we propose the PA-curve to display the distribution of sample’s correct-decision stability, which can simultaneously reflect the model’s accuracy and robustness. By calculating the area under the PA-curve, called PA-area, we enable the quantitative assessment of robustness for encrypted traffic analysis. Furthermore, we design a pre-trained model based on packet length sequence, and pre-trained it on TB-scale traffic. By fine-tuning on limited labeled training data, it can achieve downstream analysis tasks. We conduct experiments on five encrypted traffic datasets with different tasks. Besides accuracy, we analyzed the robustness of the pre-trained model and existing methods under common network disturbances, including packet loss, retransmission, and disorder. Experimental results demonstrated that, compared to ML-based and DL-based models trained from scratch, the pre-trained model can not only achieve high accuracy, but also exhibit greater resilience to network noise. The source code is available at <uri>https://github.com/Shangshu-LAB/BERT-ps</uri>","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10588-10603"},"PeriodicalIF":8.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145133823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flow Microelement-Driven Traffic Relationship Analysis: Robust Detection of Malicious Encrypted Traffic","authors":"Hao Fu;Degang Sun;Jinxia Wei;Wei Wan;Chun Long","doi":"10.1109/TIFS.2025.3613971","DOIUrl":"https://doi.org/10.1109/TIFS.2025.3613971","url":null,"abstract":"Encryption technologies randomize network communication to protect user privacy. However, attackers exploit encrypted traffic to conceal malicious activities. The existing detection methods rely primarily on traffic content or interactive patterns. Nevertheless, static methods can be easily obfuscated by advanced attacks. Since the set of potential attacks is open and infinite, models regularly lose effectiveness against novel attacks. Robust encrypted malicious traffic detection remains a valuable research area. In this paper, we propose BSTS-Net, a robust unsupervised encrypted malicious traffic detection model based entirely on traffic relations. The key motivations are to construct a relation-based traffic contextual representation and to establish dynamic baselines for anomaly detection. To represent local relations within flows, we innovatively introduce the concept of traffic microelements, which capture fine-grained interaction pattern relations. To integrate the global relationships between flows, we construct a traffic microelement space based on the Siamese neural network. Three optimization functions are proposed to optimize the intraservice, interservice and internode relations. For robust detection, we introduce a reputation-enhanced dynamic encrypted traffic detection algorithm that constructs dynamic baselines and continuously detects novel anomalies. We evaluate BSTS-Net through extensive experiments on three datasets and compare it with seven SOTA methods. Our results demonstrate its superiority, with an F1 score of more than 99.63% across all the datasets in multiclassification scenarios. Additionally, we simulate three adversarial scenarios for robustness analysis. Although the baseline methods experience an F1 score degradation of 32.21%, BSTS-Net achieves high performance, with only 1% degradation.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10604-10619"},"PeriodicalIF":8.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RLP-ABE: Puncturable CP-ABE for Efficient User Revocation From Lattices in Cloud Storage","authors":"Mengxue Yang;Huaqun Wang;Debiao He;Jiankuo Dong","doi":"10.1109/TIFS.2025.3613055","DOIUrl":"10.1109/TIFS.2025.3613055","url":null,"abstract":"Cloud computing has become the predominant platform for data sharing due to its adaptability, cost-effectiveness, and ability to scale resources according to user demand. Ensuring secure and efficient data sharing has long been a central research focus, with attribute-based encryption (ABE) serving as a key cryptographic primitive. In real-world scenarios, user attributes often change, necessitating timely revocation of access rights. Common user revocation methods include direct and indirect revocation. Direct revocation is controlled by the data owner, who adds revocation information to a list and embeds it into ciphertext to revoke permissions. Indirect revocation is managed by an authorized authority or delegated third party, dynamically publishing revocation information and generating new keys and ciphertexts. Conventional direct and indirect revocation methods incur substantial communication and computation overheads, limiting their practical effectiveness, particularly in environments with frequent user access terminations. To address these challenges, we propose a novel puncturable ciphertext-policy ABE scheme based on lattice cryptography for user revocation, eliminating the need for key regeneration and revocation-list maintenance. The proposed approach effectively resists collusion, quantum, and chosen-plaintext attacks, and experimental evaluations demonstrate its advantages in storage consumption, communication cost, and computational overhead.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"10219-10230"},"PeriodicalIF":8.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145116688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FedAMM: Federated Learning Against Majority Malicious Clients Using Robust Aggregation","authors":"Keke Gai;Dongjue Wang;Jing Yu;Liehuang Zhu;Weizhi Meng","doi":"10.1109/TIFS.2025.3607273","DOIUrl":"10.1109/TIFS.2025.3607273","url":null,"abstract":"As a collaborative framework designed to safeguard privacy, <italic>Federated Learning</i> (FL) seeks to protect participants’ data throughout the training process. However, the framework still faces security risks from poisoning attacks, arising from the unmonitored process of client-side model updates. Most existing solutions address scenarios where less than half of clients are malicious, i.e., which leaves a significant challenge to defend against attacks when more than half of partici pants are malicious. In this paper, we propose a FL scheme, named FedAMM, that resists backdoor attacks across various data distributions and malicious client ratios. We develop a novel backdoor defense mechanism to filter out malicious models, aiming to reduce the performance degradation of the model. The proposed scheme addresses the challenge of distance measurement in high-dimensional spaces by applying <italic>Principal Component Analysis</i> (PCA) to improve clustering effectiveness. We borrow the idea of critical parameter analysis to enhance discriminative ability in non-iid data scenarios, via assessing the benign or malicious nature of models by comparing the similarity of critical parameters across different models. Finally, our scheme employs a hierarchical noise perturbation to improve the backdoor mitigation rate, effectively eliminating the backdoor and reducing the adverse effects of noise on task accuracy. Through evaluations conducted on multiple datasets, we demonstrate that the proposed scheme achieves superior backdoor defense across diverse client data distributions and different ratios of malicious participants. With 80% malicious clients, FedAMM achieves low backdoor attack success rates of 1.14%, 0.28%, and 5.53% on MNIST, FMNIST, and CIFAR-10, respectively, demonstrating enhanced robustness of FL against backdoor attacks.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"9950-9964"},"PeriodicalIF":8.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145127885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}