IEEE Transactions on Information Forensics and Security最新文献

{"title":"Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP","authors":"Jiawei Kong, Hao Fang, Sihang Guo, Chenxi Qing, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Ke Xu","doi":"10.1109/tifs.2026.3723122","DOIUrl":"https://doi.org/10.1109/tifs.2026.3723122","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"4 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728445","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":"Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models","authors":"Jie Zhang, Xiangkui Cao, Zhouyu Han, Shiguang Shan, Xilin Chen","doi":"10.1109/tifs.2026.3723144","DOIUrl":"https://doi.org/10.1109/tifs.2026.3723144","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"8 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728606","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":"Backdoor Sample Detection through Progressive Perturbation and Loss Trajectory Analysis","authors":", Patrick P. K. Chan, Daniel S. Yeung","doi":"10.1109/tifs.2026.3707425","DOIUrl":"https://doi.org/10.1109/tifs.2026.3707425","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"75 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148342012","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":"AdaParse: Personalized Fingerprinting for Visual Generative Model Reverse Engineering","authors":"Yu Zheng;Zhuoxun Li;Bingyao Yu;Jie Zhou;Jiwen Lu","doi":"10.1109/TIFS.2026.3671095","DOIUrl":"10.1109/TIFS.2026.3671095","url":null,"abstract":"In this paper, we propose a hyperparameter-specialized adaptive fingerprinting framework named AdaParse for model reverse engineering, which aims at predicting hyperparameters of interest in generative models from the given AI-generated images. Existing methods rely on a single coarse model fingerprint that is originally designed for model-level attribution, which makes it difficult to distinguish fine-grained traces corresponding to different hyperparameter configurations in a multitude of generative models. To address this, our AdaParse dynamically responds to instance-level variations by estimating hyperparameter-specific fingerprints via personalizing estimation networks tailored for each input image. Specifically, our approach simultaneously learns two-branch hypernetworks that balance instance-aware and model-agnostic prior knowledge for fingerprint generation. To enable efficient network personalization, we further propose a Broadcasted Fusion module that transforms condensed feature codes into adaptive parameters through factorized weight generation with enhanced representative capacity. Extensive experiments on the large-scale public dataset across 123 generative models demonstrate that our approach outperforms previous state-of-the-art methods. Code available at <uri>https://github.com/lizhuoxun/AdaParse/</uri>","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2682-2697"},"PeriodicalIF":8.0,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371543","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":"MithrilRB: Resource-Efficient Redactable Blockchain With Single-Use Authorization","authors":"Tianming Hou;Hui Ma;Jinchao Zhang;Yang Li;Bo Li;Weiping Wang","doi":"10.1109/TIFS.2026.3671133","DOIUrl":"10.1109/TIFS.2026.3671133","url":null,"abstract":"Redactable blockchains preserve the integrity of hash links while enabling authorized redactions to comply with regulatory requirements. However, existing permissioned solutions suffer from three severe issues. First, fine-grained privilege control incurs significant storage overhead, especially in the case of single-use authorization. Second, the reliance on bilinear pairings in chameleon hash leads to significant performance degradation when handling large-scale redaction requests. Finally, multiple incorporated components often unconsciously introduce centralized entities, undermining the decentralized nature. In this paper, we propose MithrilRB, a resource-efficient and decentralized redactable blockchain with single-use authorization. Specifically, we introduce a privilege control mechanism with our proposed multi-authority attribute-based signature (MA-ABS) and the threshold BLS signature, achieving fine-grained single-use authorization and direct user revocation without extra ciphertext storage. We also design a pairing-free non-interactive threshold chameleon hash (PNITCH), which enhances efficiency and is better suited for large-scale redaction requests. Moreover, MithrilRB eliminates centralized trust points that hold secret information, ensuring fully decentralization-compatible functional integration in redactable blockchains. Finally, we implement MithrilRB, and the experimental results demonstrate that MithrilRB significantly outperforms existing solutions in both computational efficiency and storage requirements.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2698-2712"},"PeriodicalIF":8.0,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371510","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":"TFSCL: A Novel Time-Frequency Similarity Contrastive Learning Method With Hybrid Augmentation for Robust and Accurate Specific Emitter Identification","authors":"Kaixuan Huang;Yongtao Ma;Jialu Zhu;Yuxiang Han","doi":"10.1109/TIFS.2026.3671097","DOIUrl":"10.1109/TIFS.2026.3671097","url":null,"abstract":"As the Internet of Things (IoT) and Sixth Generation (6G) technologies advance rapidly, the cryptographic identification of electronic devices has become a critical issue in information security. Radio frequency fingerprint (RFF)-based specific emitter identification (SEI) has emerged as a prominent physical-layer authentication technique. To enhance the stability and accuracy of multi-target recognition in complex electromagnetic environments, a novel technique for specific emitter identification based on time-frequency similarity contrastive learning (TFSCL) is proposed. In this study, we present a novel pre-training method utilizing a deep complex-valued pyramid network (DCPN) to enhance the extraction and reconstruction of time series and frequency domain sequences. The DCPN enables contrastive learning of signal features in both the temporal and frequency domains, significantly reducing computational complexity and improving pretraining performance. Additionally, we first introduce the Time-Frequency Synchronization Data Added (TFS-DA), a Time-Frequency Hybrid Data Added Technique that employs Gray code to generate random sequences, effectively improving feature representation in both domains. Empirical results demonstrate that the proposed method achieves an accuracy rate of 97.12% on an automatic-dependent surveillance-broadcast (ADS-B) dataset that contains 10 categories with only data labeled 10%. On a LoRa dataset containing 30 categories with only data labeled 10%, the accuracy rate reaches 77.06%.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2668-2681"},"PeriodicalIF":8.0,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371545","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":"Efficient Byzantine-Robust Privacy-Preserving Federated Learning via Dimension Compression","authors":"Xian Qin;Xue Yang;Xiaohu Tang","doi":"10.1109/TIFS.2026.3671104","DOIUrl":"https://doi.org/10.1109/TIFS.2026.3671104","url":null,"abstract":"Federated Learning (FL) allows collaborative model training across distributed clients without sharing raw data, thus preserving privacy. However, the system remains vulnerable to privacy leakage from gradient updates and Byzantine attacks from malicious clients. Existing solutions face a critical trade-off among privacy preservation, Byzantine robustness, and computational efficiency. We propose a novel scheme that effectively balances these competing objectives by integrating homomorphic encryption with dimension compression based on the Johnson-Lindenstrauss transformation. Our approach employs a dual-server architecture that enables secure Byzantine defense in the ciphertext domain while dramatically reducing computational overhead through gradient compression. The dimension compression technique preserves the geometric relationships necessary for Byzantine defence while reducing computation complexity from <inline-formula> <tex-math>$O(dn)$ </tex-math></inline-formula> to <inline-formula> <tex-math>$O(kn)$ </tex-math></inline-formula> cryptographic operations, where <inline-formula> <tex-math>$k ll d$ </tex-math></inline-formula>. Extensive experiments across diverse datasets demonstrate that our approach maintains model accuracy comparable to non-private FL while effectively defending against Byzantine clients comprising up to 40% of the network. Our approach also demonstrates substantial improvements in computational and communication efficiency. Experimental evaluation shows that the dimension compression technique achieves <inline-formula> <tex-math>$25 times sim 35 times $ </tex-math></inline-formula> reduction in computational overhead and <inline-formula> <tex-math>$17 times $ </tex-math></inline-formula> reduction in communication overhead compared to our non-compression version. When compared to state-of-the-art methods like ShieldFL, our approach demonstrates order-of-magnitude improvements in both computational and communication efficiency while maintaining equivalent privacy guarantees and achieving superior Byzantine robustness comparable to FLTrust. These substantial efficiency enhancements make secure FL practical for deployment in large-scale neural networks with millions of parameters.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2596-2609"},"PeriodicalIF":8.0,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440573","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":"Bi-Level Inter-Modality Modulation for Unsupervised Visible-Infrared Person Re-Identification","authors":"Jinjia Peng;Junyu Liu;Xutao Zuo;Zeze Tao;Huibing Wang","doi":"10.1109/TIFS.2026.3671087","DOIUrl":"10.1109/TIFS.2026.3671087","url":null,"abstract":"The task of unsupervised visible–infrared person re-identification (USL-VI-ReID) aims to retrieve cross-modal pedestrian images without manual annotations. The key challenge lies in achieving semantic alignment to resolve modality bias in the absence of real labels. However, existing methods overly rely on single-modal information in the process of pseudo-label generation without considering cross-modal associations, making it difficult to bridge the modality gap between visible and infrared images. To address these issues, this paper proposes a Bi-level Inter-Modal Modulation Network (BIMM-Net), which employs multi-level cluster structure optimization as a core strategy to drive the establishment of cross-modal semantic associations, ultimately achieving cross-modal alignment at the feature representation level. Specifically, we construct a novel intermediary modality GrayMix from visible images to enhance model robustness against color variations and alleviate modality gaps. To filter out noise in cross-modal matching and establish a shared semantic space between visible and infrared modalities, we further develop a Ternary Pairs Calibration-Convergence module designed for filtering noise from visible-infrared cluster matching, on this basis constructing fused mixture clusters. Building on this mixture cluster space, an Heterogeneous-Isomorphic Alignment Loss is also designed to align the feature distributions of the three modalities, reinforcing cross-modal semantic consistency. In addition, we present a Cross-modal Neighborhood Consistency Clustering method, which facilitates the formation and propagation of cross-modal clusters by selecting high-confidence cross-modal neighbor pairs and refining feature distances. Ultimately, BIMM-Net through the joint modeling of bi-level clustering enables multiple levels to guide each other in refining cross-modal structures, thereby effectively establishing the semantic associations between visible and infrared modalities. Extensive experiments validate the superior performance of the proposed framework, achieving state-of-the-art results in USL-VI-ReID. The source code of this paper is available at: <uri>https://github.com/liujuny5920/DIMM-Net</uri>","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2652-2667"},"PeriodicalIF":8.0,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371542","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":"Toward Robust Radio Frequency Fingerprint Identification: A Federated Learning Framework With Feature Alignment","authors":"Yuteng Wang;Zhenxin Cai;Tiantian Tang;Tomoaki Ohtsuki;Guan Gui","doi":"10.1109/TIFS.2026.3671107","DOIUrl":"10.1109/TIFS.2026.3671107","url":null,"abstract":"With the growing adoption of Internet of Things (IoT) devices, ensuring the security of wireless communications has become increasingly critical. Radio frequency fingerprint identification (RFFI) has shown promise in this regard due to its capability of uniquely identifying devices. Although deep learning (DL) approaches have significantly improved RFFI performance, they typically rely on large-scale centralized data. This poses challenges in terms of privacy preservation and heterogeneous data distributions. To address the performance degradation caused by non-independent and identically distributed (non-IID) data in cross-receiver scenarios, this paper proposes a feature alignment strategy based on federated learning (FL) for RFFI. In such scenarios, due to differences in receiver hardware characteristics, deployment locations, and channel conditions, the signals captured by different receivers often exhibit distribution shifts, resulting in misaligned feature spaces across clients. The proposed method guides each client to learn aligned intermediate feature representations during local training, effectively mitigating the resulting adverse impact on model generalization. Experiments conducted on a real-world RF dataset demonstrate that the proposed method achieves higher identification accuracy and improved stability compared with representative federated baselines, including FedAvg and FedProx. The highest identification accuracy reaches 90.83%, and the performance gains are accompanied by generally reduced variance across different client configurations, highlighting the robustness and generalization capability of the proposed approach in heterogeneous wireless environments.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2641-2651"},"PeriodicalIF":8.0,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371509","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":"OwnerHunter: Multilingual Website Owner Identification Powered by Large Language Model","authors":"Cheng Tu;Enhuan Dong;Yunyi Zhang;Shiyu Wang;Zexiang Zhang;Min Zhang;Yang Li;Pengfei Xue;Jiahai Yang","doi":"10.1109/TIFS.2026.3666852","DOIUrl":"10.1109/TIFS.2026.3666852","url":null,"abstract":"As cyberspace continues to expand, identifying the organization or individual behind a website has become increasingly vital in security incident response, phishing website detection, and other cybersecurity subfields. An existing solution for it involves analyzing webpage content and extracting owner names using named entity recognition techniques. However, since these techniques operate on a sentence-by-sentence basis, they struggle to identify the true owner when multiple individual or organizational names appear on a webpage. Moreover, they often perform poorly on non-English websites. To address these limitations, we propose OwnerHunter,<xref>1</xref> a novel multilingual framework powered by large language models, which formulates website owner identification as a multilingual document-level information extraction task and utilizes global information from webpages to identify the owner. In OwnerHunter, we first craft prompts that fully leverage the capabilities of large language models to effectively recognize potential owners on webpages in different languages with minimal examples. To enhance the comprehensiveness and accuracy of recognition, we further design a multimodal augmentation strategy, an example pool strategy, and a self-verification strategy. Then, we devise a semantic and string similarity aggregation-based entity disambiguation technique to eliminate ambiguities among multiple potential owners recognized by large language models and a position-based hybrid ranking technique to exactly select the true owner. To evaluate OwnerHunter, we refine the publicly available English dataset ONER and construct the Chinese dataset WOI-cn with 16,036 real websites. Experimental results show that OwnerHunter achieves F1 scores of 0.9505 on ONER and 0.9621 on WOI-cn, setting new state-of-the-art performance on both datasets.<fn><label>¹</label><p>Codes are available at <uri>https://github.com/tuchen9/OwnerHunter</uri></p></fn>","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2430-2445"},"PeriodicalIF":8.0,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147350973","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}