Pub Date : 2026-01-15DOI: 10.1109/tifs.2026.3654865
Xiuwen Liu, Yanjiao Chen, Shanchen Pang
{"title":"Decision Boundary-aware Counterfactual Learning against Model Extraction Attacks on Graph Neural Networks","authors":"Xiuwen Liu, Yanjiao Chen, Shanchen Pang","doi":"10.1109/tifs.2026.3654865","DOIUrl":"https://doi.org/10.1109/tifs.2026.3654865","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"39 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145972196","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":"Bridging Lab and Industry: Practical SPA-GPT on Cryptosystems Boosted by LSTM and Simulated Annealing","authors":"Ziyu Wang, Yaoling Ding, An Wang, Congming Wei, Jingqi Zhang, Liehuang Zhu","doi":"10.1109/tifs.2026.3654798","DOIUrl":"https://doi.org/10.1109/tifs.2026.3654798","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"177 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145972197","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 : 2026-01-14DOI: 10.1109/tifs.2026.3651978
Shuhan Qi, Qinglin Zhao, Zijie Liu, MengChu Zhou, Meng Shen, Peiyun Zhang, Yi Sun
{"title":"Modeling the Performance-Security Trade-off of Gasper’s Block Proposal Mechanism Under Latency-Driven Attacks","authors":"Shuhan Qi, Qinglin Zhao, Zijie Liu, MengChu Zhou, Meng Shen, Peiyun Zhang, Yi Sun","doi":"10.1109/tifs.2026.3651978","DOIUrl":"https://doi.org/10.1109/tifs.2026.3651978","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"60 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145972217","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":"RIS-Assisted Integrated Communication and Secret Key Generation in Quasi-Static Environments","authors":"Zheyuan Deng, Xiaoyan Hu, Keming Ma, Liang Jin, Boming Li, Jinghua Qu","doi":"10.1109/tifs.2026.3654398","DOIUrl":"https://doi.org/10.1109/tifs.2026.3654398","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"267 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145972226","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 : 2026-01-14DOI: 10.1109/tifs.2026.3654388
Sk Tanzir Mehedi, Chadni Islam, Gowri Ramachandran, Raja Jurdak
{"title":"DySec: A Machine Learning-based Dynamic Analysis for Detecting Malicious Packages in PyPI Ecosystem","authors":"Sk Tanzir Mehedi, Chadni Islam, Gowri Ramachandran, Raja Jurdak","doi":"10.1109/tifs.2026.3654388","DOIUrl":"https://doi.org/10.1109/tifs.2026.3654388","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"5 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145972220","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}
Vertical Split Federated Learning (VSFL) allows participants to collaboratively train a better model with different features vertically partitioned in the same sample space, where the model is divided into bottom model and top model by the cut layer, trained by passive and active participants respectively. However, in the process, the labels owned by the active participant will still be inferred or stolen by curious or malicious passive participants. In this paper, we propose Casper, a causality-inspired defense mechanism with a confounder against label inference attacks in VSFL. Casper first analyzes the feasibility of optimizing the training process in VSFL at the intervention level from a causal perspective. It then introduces a confounder consisting of cut layer output reconstruction and label obfuscation to disrupt the direct causality between cut layer outputs and labels. Additionally, we integrate selective discrepancy training to further ensure model utility by strategically balancing training between active and passive participants. Extensive experiments conducted on four datasets across different tasks demonstrate that Casper effectively preserves label privacy while maintaining model performance, significantly outperforming current advanced defending methods in VSFL.
{"title":"Casper: A Causality-Inspired Defense With Confounder Against Label Inference Attacks in Vertical Split Federated Learning","authors":"Meng Shen;Jin Meng;Bohan Peng;Xiangyun Tang;Wei Wang;Dusit Niyato;Liehuang Zhu","doi":"10.1109/TIFS.2026.3652013","DOIUrl":"https://doi.org/10.1109/TIFS.2026.3652013","url":null,"abstract":"Vertical Split Federated Learning (VSFL) allows participants to collaboratively train a better model with different features vertically partitioned in the same sample space, where the model is divided into bottom model and top model by the cut layer, trained by passive and active participants respectively. However, in the process, the labels owned by the active participant will still be inferred or stolen by curious or malicious passive participants. In this paper, we propose Casper, a causality-inspired defense mechanism with a confounder against label inference attacks in VSFL. Casper first analyzes the feasibility of optimizing the training process in VSFL at the intervention level from a causal perspective. It then introduces a confounder consisting of cut layer output reconstruction and label obfuscation to disrupt the direct causality between cut layer outputs and labels. Additionally, we integrate selective discrepancy training to further ensure model utility by strategically balancing training between active and passive participants. Extensive experiments conducted on four datasets across different tasks demonstrate that Casper effectively preserves label privacy while maintaining model performance, significantly outperforming current advanced defending methods in VSFL.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"1050-1064"},"PeriodicalIF":8.0,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026471","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 : 2026-01-12DOI: 10.1109/TIFS.2026.3651997
Di Li;Chun Li;Yufeng Tang;Yupeng Zhang;Zheng Gong
Inconsistencies in manufacturing features, sampling settings, and cryptographic implementations amongst the profiling and target devices can lead to the failure of profiling side-channel analysis (SCA). Various techniques, such as preprocessing, multi-device training, and transfer learning, have been proposed to mitigate this portability problem in profiling SCA. However, many techniques of block ciphers, such as tweaks, key-dependent components, and customized elements, might have uncertain effects from the perspective of cryptographic implementations, requiring further insightful analysis on their impact on portability. This paper investigates the portability of profiling SCA from a case study using adjustable implementations of block ciphers. First, we theoretically analyze the variation in leakage distribution under adjustable implementations. To support our theoretical results, a dataset of deep-learning SCA is built from AES, Pilsung, and Skinny. Specifically, we reveal how to reverse the parameterized components and recover the key from these adjustable implementations. According to our experiment on an 8-bit AVR microcontroller, the computational complexities of the attacks based on our model are less than $9times 2^{16}$ within 4500 traces. Moreover, the effectiveness of our proposed method is demonstrated under the combinatorial effect with adjustable implementations and device characteristics. Our case study provides insights into the results of adjustable implementations of block ciphers, which strengthens both the theoretical and practical understanding of the portability of profiling SCA.
{"title":"Portability of Profiling Side-Channel Analysis: A Case Study Using Adjustable Implementations of Block Ciphers","authors":"Di Li;Chun Li;Yufeng Tang;Yupeng Zhang;Zheng Gong","doi":"10.1109/TIFS.2026.3651997","DOIUrl":"https://doi.org/10.1109/TIFS.2026.3651997","url":null,"abstract":"Inconsistencies in manufacturing features, sampling settings, and cryptographic implementations amongst the profiling and target devices can lead to the failure of profiling side-channel analysis (SCA). Various techniques, such as preprocessing, multi-device training, and transfer learning, have been proposed to mitigate this portability problem in profiling SCA. However, many techniques of block ciphers, such as tweaks, key-dependent components, and customized elements, might have uncertain effects from the perspective of cryptographic implementations, requiring further insightful analysis on their impact on portability. This paper investigates the portability of profiling SCA from a case study using adjustable implementations of block ciphers. First, we theoretically analyze the variation in leakage distribution under adjustable implementations. To support our theoretical results, a dataset of deep-learning SCA is built from AES, Pilsung, and Skinny. Specifically, we reveal how to reverse the parameterized components and recover the key from these adjustable implementations. According to our experiment on an 8-bit AVR microcontroller, the computational complexities of the attacks based on our model are less than <inline-formula> <tex-math>$9times 2^{16}$ </tex-math></inline-formula> within 4500 traces. Moreover, the effectiveness of our proposed method is demonstrated under the combinatorial effect with adjustable implementations and device characteristics. Our case study provides insights into the results of adjustable implementations of block ciphers, which strengthens both the theoretical and practical understanding of the portability of profiling SCA.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"1021-1035"},"PeriodicalIF":8.0,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982335","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 : 2026-01-12DOI: 10.1109/TIFS.2026.3652010
Chen Zhu;Yang Lu;Nian Xia;Jiguo Li;Yinxia Sun
Data Integrity Auditing (DIA) enables users to remotely verify whether their data saved in third-party clouds has been maliciously tampered with or compromised. As an extension of DIA in certificateless cryptography, certificateless DIA (CL-DIA) integrates the merits of conventional public-key cryptography (no key escrow) and identity-based cryptography (no certificates). However, CL-DIA schemes depend on a reliable third-party auditor (TPA) to perform integrity audits, inevitably suffering from performance bottleneck and single-point failure problems. Moreover, almost all current CL-DIA schemes were designed with computationally expensive bilinear pairings. Cryptanalysis demonstrates that the existing unique pairing-free CL-DIA scheme fails to achieve the unforgeable security of auditing proofs. In this work, we put forward a lightweight blockchain-assisted CL-DIA scheme. The scheme achieves DIA through the blockchain instead of a single TPA, thereby overcoming the problems caused by the TPA-based centralized auditing model. Then, by avoiding time-consuming pairing operations and employing edge servers in generating verifiable tags for the uploaded data of users, its performance surpasses previous pairing-based CL-DIA schemes, particularly in terms of computation efficiency. Furthermore, we provide formal proofs in the random oracle model demonstrating that our scheme achieves unforgeability of verifiable tags and auditing proofs, ensures data privacy secrity, and is resistant to collusion attacks between the EN and the CSP. Finally, experimental results show that when auditing 25 file blocks, our scheme only costs 0.29s, which reduces the total time cost of integrity auditing phase by 48.2%-85.5% compared to current pairing-based CL-DIA schemes.
{"title":"A Lightweight Blockchain-Assisted Certificateless Cloud Data Integrity Auditing Scheme Without Third-Party Auditor","authors":"Chen Zhu;Yang Lu;Nian Xia;Jiguo Li;Yinxia Sun","doi":"10.1109/TIFS.2026.3652010","DOIUrl":"https://doi.org/10.1109/TIFS.2026.3652010","url":null,"abstract":"Data Integrity Auditing (DIA) enables users to remotely verify whether their data saved in third-party clouds has been maliciously tampered with or compromised. As an extension of DIA in certificateless cryptography, certificateless DIA (CL-DIA) integrates the merits of conventional public-key cryptography (no key escrow) and identity-based cryptography (no certificates). However, CL-DIA schemes depend on a reliable third-party auditor (TPA) to perform integrity audits, inevitably suffering from performance bottleneck and single-point failure problems. Moreover, almost all current CL-DIA schemes were designed with computationally expensive bilinear pairings. Cryptanalysis demonstrates that the existing unique pairing-free CL-DIA scheme fails to achieve the unforgeable security of auditing proofs. In this work, we put forward a lightweight blockchain-assisted CL-DIA scheme. The scheme achieves DIA through the blockchain instead of a single TPA, thereby overcoming the problems caused by the TPA-based centralized auditing model. Then, by avoiding time-consuming pairing operations and employing edge servers in generating verifiable tags for the uploaded data of users, its performance surpasses previous pairing-based CL-DIA schemes, particularly in terms of computation efficiency. Furthermore, we provide formal proofs in the random oracle model demonstrating that our scheme achieves unforgeability of verifiable tags and auditing proofs, ensures data privacy secrity, and is resistant to collusion attacks between the EN and the CSP. Finally, experimental results show that when auditing 25 file blocks, our scheme only costs 0.29s, which reduces the total time cost of integrity auditing phase by 48.2%-85.5% compared to current pairing-based CL-DIA schemes.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"976-991"},"PeriodicalIF":8.0,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026561","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：