Pub Date : 2026-01-27DOI: 10.1109/tifs.2026.3657840
Rui Hou, Li Jia, Xuhui Bu, Jianfang Li
{"title":"Event-Triggered Model-Free Adaptive Predictive Control for Networked Wind-Power Microgrids Subject to Aperiodic DoS Attacks","authors":"Rui Hou, Li Jia, Xuhui Bu, Jianfang Li","doi":"10.1109/tifs.2026.3657840","DOIUrl":"https://doi.org/10.1109/tifs.2026.3657840","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"295 1","pages":"1-1"},"PeriodicalIF":6.8,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146056324","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}
Pub Date : 2026-01-26DOI: 10.1109/TIFS.2026.3657891
Zekun Sun;Liwei Liu;Zhe Li;Tianyu Wang;Zhihao Sui;Na Ruan;Conghui He;Dahua Lin;Jianhua Li
In the realm of deep learning, the veracity and integrity of the training data are pivotal for constructing reliable and transparent models. This study introduces the concept of Trustworthy Dataset Proof (TDP), which tackles the significant challenge of verifying the authenticity of training data as declared by trainers. Existing dataset provenance methods, which primarily aim at ownership verification rather than trust enhancement, often face challenges with usability and integrity. For instance, excessive operational demands and the inability to effectively verify dataset authenticity hinder their practical application. To address these shortcomings, we propose a novel technique termed Data Probe, which diverges from traditional watermarking by utilizing subtle variations in model output distributions to confirm the presence of a specific and small subset of training data. This model-agnostic approach improves usability by minimizing the intervention during the training process and ensures dataset integrity via a mechanism that only permits probe detection when the entire claimed dataset is utilized in training. Our study conducts extensive evaluations to demonstrate the effectiveness of the proposed data-probe-based TDP framework, marking a significant step toward achieving transparency and trustworthiness in the use of training data in deep learning.
{"title":"Trustworthy Dataset Proof: Certifying the Authentic Use of Dataset in Training Models for Enhanced Trust","authors":"Zekun Sun;Liwei Liu;Zhe Li;Tianyu Wang;Zhihao Sui;Na Ruan;Conghui He;Dahua Lin;Jianhua Li","doi":"10.1109/TIFS.2026.3657891","DOIUrl":"10.1109/TIFS.2026.3657891","url":null,"abstract":"In the realm of deep learning, the veracity and integrity of the training data are pivotal for constructing reliable and transparent models. This study introduces the concept of Trustworthy Dataset Proof (TDP), which tackles the significant challenge of verifying the authenticity of training data as declared by trainers. Existing dataset provenance methods, which primarily aim at ownership verification rather than trust enhancement, often face challenges with usability and integrity. For instance, excessive operational demands and the inability to effectively verify dataset authenticity hinder their practical application. To address these shortcomings, we propose a novel technique termed Data Probe, which diverges from traditional watermarking by utilizing subtle variations in model output distributions to confirm the presence of a specific and small subset of training data. This model-agnostic approach improves usability by minimizing the intervention during the training process and ensures dataset integrity via a mechanism that only permits probe detection when the entire claimed dataset is utilized in training. Our study conducts extensive evaluations to demonstrate the effectiveness of the proposed data-probe-based TDP framework, marking a significant step toward achieving transparency and trustworthiness in the use of training data in deep learning.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"1902-1913"},"PeriodicalIF":8.0,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146056326","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}
Pub Date : 2026-01-23DOI: 10.1109/tifs.2026.3657051
Guowei Ling, Peng Tang, Shi-Feng Sun, Weidong Qiu
{"title":"Efficient Updatable PSI from Asymmetric PSI and PSU","authors":"Guowei Ling, Peng Tang, Shi-Feng Sun, Weidong Qiu","doi":"10.1109/tifs.2026.3657051","DOIUrl":"https://doi.org/10.1109/tifs.2026.3657051","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"11226 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043059","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}
Pub Date : 2026-01-23DOI: 10.1109/TIFS.2026.3657031
Arman Ahmad;S. Jagatheswari
Blockchain-enabled Internet of Medical Things (BIoMT) systems require secure and anonymous authentication. However, existing mechanisms rely on classical cryptography, which becomes vulnerable to quantum attacks. This creates a critical need for post-quantum secure authentication that can preserve anonymity while remaining lightweight for large-scale deployments. To address this gap, we propose a module-lattice based Post-Quantum Aggregate Blind Signature (PQ-ABS) scheme that combines message blindness, signature aggregation, and Module-LWE hardness to achieve anonymous and quantum-resistant authentication. The scheme integrates with a lightweight blockchain architecture in which multiple signatures from distributed medical entities are aggregated into a single compact proof, significantly reducing verification overhead as the number of nodes increases. Formal analysis demonstrates resistance against correctness, unforgeability, blindness, unlinkability, and its resilience against quantum polynomial-time (QPT) adversaries under Module-SIS and Module-LWE assumptions. A full implementation on Hyperledger Fabric shows that, under growing network size, proposed PQ-ABS framework reduces verification latency by up to 71%, improves throughput by 62%, and maintains stable performance as the blockchain scales, confirming both its security and efficiency for real-time BIoMT environments.
{"title":"PQ-ABS: Post-Quantum Aggregate Blind Signature-Based Anonymous Authentication for Blockchain-Enabled IoMT","authors":"Arman Ahmad;S. Jagatheswari","doi":"10.1109/TIFS.2026.3657031","DOIUrl":"10.1109/TIFS.2026.3657031","url":null,"abstract":"Blockchain-enabled Internet of Medical Things (BIoMT) systems require secure and anonymous authentication. However, existing mechanisms rely on classical cryptography, which becomes vulnerable to quantum attacks. This creates a critical need for post-quantum secure authentication that can preserve anonymity while remaining lightweight for large-scale deployments. To address this gap, we propose a module-lattice based Post-Quantum Aggregate Blind Signature (PQ-ABS) scheme that combines message blindness, signature aggregation, and Module-LWE hardness to achieve anonymous and quantum-resistant authentication. The scheme integrates with a lightweight blockchain architecture in which multiple signatures from distributed medical entities are aggregated into a single compact proof, significantly reducing verification overhead as the number of nodes increases. Formal analysis demonstrates resistance against correctness, unforgeability, blindness, unlinkability, and its resilience against quantum polynomial-time (QPT) adversaries under Module-SIS and Module-LWE assumptions. A full implementation on Hyperledger Fabric shows that, under growing network size, proposed PQ-ABS framework reduces verification latency by up to 71%, improves throughput by 62%, and maintains stable performance as the blockchain scales, confirming both its security and efficiency for real-time BIoMT environments.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"1542-1551"},"PeriodicalIF":8.0,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043058","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}
Pub Date : 2026-01-23DOI: 10.1109/tifs.2026.3657036
Yipeng Zou, Qin Liu, Jie Wu, Tian Wang, Guo Chen, Tao Peng, Guojun Wang
{"title":"CAA: Toward Camouflaged and Transferable Adversarial Examples","authors":"Yipeng Zou, Qin Liu, Jie Wu, Tian Wang, Guo Chen, Tao Peng, Guojun Wang","doi":"10.1109/tifs.2026.3657036","DOIUrl":"https://doi.org/10.1109/tifs.2026.3657036","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"50 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043057","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":"PHANTOM: Power Hammering Attack and Countermeasure on Multi-Tenant ReRAM Compute-in-Memory Accelerators","authors":"Ashish Reddy Bommana, Rajendra Bishnoi, Naghmeh Karimi, Farshad Firouzi, Krishnendu Chakrabarty","doi":"10.1109/tifs.2026.3657612","DOIUrl":"https://doi.org/10.1109/tifs.2026.3657612","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"57 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043056","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":"Cross-Region Feature Reformer with Semantic Preservation for Adversarial Malware Detection","authors":"Qian Li, Di Wu, Chenhao Lin, Shuai Liu, Cong Wang, Chao Shen","doi":"10.1109/tifs.2026.3657117","DOIUrl":"https://doi.org/10.1109/tifs.2026.3657117","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"40 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043060","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}
Pub Date : 2026-01-22DOI: 10.1109/tifs.2026.3657043
Jie Gui, Yu-Xin Zhang, Xiaofeng Cong, Baosheng Yu, Zhipeng Gui, Yuan Yan Tang, James Tin-Yau Kwok
{"title":"Axial-View-Oriented Contrastive Adversarial Training for Robust Point Cloud Recognition","authors":"Jie Gui, Yu-Xin Zhang, Xiaofeng Cong, Baosheng Yu, Zhipeng Gui, Yuan Yan Tang, James Tin-Yau Kwok","doi":"10.1109/tifs.2026.3657043","DOIUrl":"https://doi.org/10.1109/tifs.2026.3657043","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"40 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043078","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：