IEEE Transactions on Information Forensics and Security最新文献

RegexStealer: A Directed-Acyclic-Graph-based Regex Stealing Against Web Application Firewalls RegexStealer：一种针对Web应用防火墙的基于定向无循环图的正则表达式窃取

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-09-28 DOI: 10.1109/tifs.2026.3737638

Deyin Li, Xiang Ling, Xiang Chen, Chunming Wu, Xuan Liu, Muhammad Khurram Khan

引用次数: 0

Dual-Domain Graph–Pixel Fusion Network for Iris Segmentation 用于虹膜分割的双域图像素融合网络

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-09-28 DOI: 10.1109/tifs.2026.3737637

Zhuoru Li, Xiaowei Bai, Yingxi Li, Hao He, Liang Xie, Erwei Yin

引用次数: 0

Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling 通过结构化视觉叙事破解多模态大型语言模型的连续漫画

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-09-18 DOI: 10.1109/tifs.2026.3734766

Deyue Zhang, Dongdong Yang, Junjie Mu, Quanchen Zou, Zonghao Ying, Wenzhuo Xu, Zhao Liu, Xuan Wang, Xiangzheng Zhang

引用次数: 0

CAN-SHIELD: A Sensitive Hierarchical Intelligent Encryption and Layered Defense Mechanism for In-Vehicle CAN systems CAN- shield：车载CAN系统的敏感分层智能加密和分层防御机制

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-09-17 DOI: 10.1109/tifs.2026.3734784

Xinze Li, Jin Cao, Ben Niu, Chao Shang, Yinghui Zhang, Hui Li

引用次数: 0

From Unknown to Known: Enhancing BGP Route Origin Validation with Multi-Source Data 从未知到已知：用多源数据增强BGP路由起源验证

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-09-17 DOI: 10.1109/tifs.2026.3734744

Jia Zhang, Shaorui Ren, Andong Chen, Shuhe Wang, Yangyang Wang, Jiahao Cao, Mingwei Xu, Jiayu Zheng

引用次数: 0

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP 神经解毒剂：类明智的提示调谐净化后门在CLIP

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-08-12 DOI: 10.1109/tifs.2026.3723122

Jiawei Kong, Hao Fang, Sihang Guo, Chenxi Qing, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Ke Xu

引用次数: 0

Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models Multi-PA：大型视觉语言模型隐私评估的多视角基准

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-08-12 DOI: 10.1109/tifs.2026.3723144

Jie Zhang, Xiangkui Cao, Zhouyu Han, Shiguang Shan, Xilin Chen

引用次数: 0

Backdoor Sample Detection through Progressive Perturbation and Loss Trajectory Analysis 基于渐进式扰动和损失轨迹分析的后门样本检测

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-06-25 DOI: 10.1109/tifs.2026.3707425

, Patrick P. K. Chan, Daniel S. Yeung

引用次数: 0

AdaParse: Personalized Fingerprinting for Visual Generative Model Reverse Engineering 用于视觉生成模型逆向工程的个性化指纹识别

IF 8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-03-05 DOI: 10.1109/TIFS.2026.3671095

Yu Zheng;Zhuoxun Li;Bingyao Yu;Jie Zhou;Jiwen Lu

{"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}

引用次数: 0

MithrilRB: Resource-Efficient Redactable Blockchain With Single-Use Authorization MithrilRB：具有单次使用授权的资源高效可读区块链

IF 8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2026-03-05 DOI: 10.1109/TIFS.2026.3671133

Tianming Hou;Hui Ma;Jinchao Zhang;Yang Li;Bo Li;Weiping Wang

{"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}

引用次数: 0