IEEE Transactions on Information Forensics and Security最新文献

Gradient-Aware Adaptive Meta-Prompt Learner for Generalizable Face Forgery Detection 基于梯度感知的自适应元提示学习器的人脸伪造检测

IF 8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-17 DOI: 10.1109/TIFS.2025.3622981

Hanqing Liu;Hongxia Wang;Rui Zhang;Yang Zhou;Qiang Zeng

{"title":"Gradient-Aware Adaptive Meta-Prompt Learner for Generalizable Face Forgery Detection","authors":"Hanqing Liu;Hongxia Wang;Rui Zhang;Yang Zhou;Qiang Zeng","doi":"10.1109/TIFS.2025.3622981","DOIUrl":"10.1109/TIFS.2025.3622981","url":null,"abstract":"The misuse of AI-generated techniques in face forgery has raised significant concerns, driving advancements in detection methods. However, existing algorithms struggle with generalization in cross-domain scenarios due to domain shifts, limiting their practical applications. Prompt tuning, which learns soft prompts while freezing the backbone, enables the generalizable Vision-Language Models (VLMs) pre-trained on large-scale datasets to adapt to downstream tasks. Though effective, prompt tuning confronts challenges in face forgery detection, where its performance is sensitive to initialization and may undermine the generalizability of pre-trained VLMs. To address this issue, we propose a novel Gradient-aware Adaptive Meta-Prompt Learner (GAMP-Learner). The core idea is to learn a meta-general gradient from multiple source domains through the Direction-shared Gradient Pruning Module (DGPM) for efficient initialization in the inner-loop, while addressing gradient conflicts via the Adaptive Gradient Calibration Module (AdaGCM) to enhance generalization in the outer-loop. Notably, our GAMP-Learner can be seamlessly integrated into any prompt-based fine-tuning VLM in a model-agnostic way. Additionally, to capture fine-grained forgery clues, we design a Multi-Granularity Conditional Prompt Generator (MGCP), which constructs instance-level prompts by incorporating multi-scale content-style feature representations. Simulating practical scenarios, we devise three protocols which evaluate generalization performance trained on multiple source domains. Extensive experiments demonstrate that the proposed framework achieves competitive cross-domain detection performance compared to state-of-the-art methods.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"11208-11222"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145310988","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

Boosting Parallel Fuzzing with Boundary-Targeted Task Allocation and Exploration 基于边界目标任务分配与探索的并行模糊算法

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-17 DOI: 10.1109/tifs.2025.3622956

Hong Liang, Yijia Guo, Haotian Wu, Yifan Xia, Yi Xiang, Xiantao Jin, Hao Peng, Xuhong Zhang, Shouling Ji

引用次数: 0

The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems 捷足先登：揭示LLM服务系统中的时序侧信道

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-17 DOI: 10.1109/tifs.2025.3622954

Linke Song, Zixuan Pang, Wenhao Wang, Zihao Wang, XiaoFeng Wang, Hongbo Chen, Wei Song, Yier Jin, Dan Meng, Rui Hou

引用次数: 0

Unlocking Mobile Phones by Rolling Wrists: A Novel Motion-based Biometric Recognition Method 通过滚动手腕解锁手机：一种新的基于动作的生物识别方法

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-17 DOI: 10.1109/tifs.2025.3622964

Yadi He, Sitan Chen, Linfeng Liu

引用次数: 0

Polar-Domain Multi-User Key Generation in Near-Field Communications 近场通信中极域多用户密钥生成

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-16 DOI: 10.1109/tifs.2025.3622317

Tianyu Lu, Liquan Chen, Junqing Zhang, Weicheng Zhang, Michail Matthaiou

引用次数: 0

Jamming and Impulsive Noise Uncertainty Aided Covert Communication in PLC Networks 干扰和脉冲噪声不确定性辅助PLC网络隐蔽通信

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-16 DOI: 10.1109/tifs.2025.3622369

Rui Chen, Jianqiang Chen, Shouzhi Xu, Xingwang Li, Xiaojun Liu

引用次数: 0

Practical Constant-Time Asynchronous Distributed Key Generation with Improved Efficiency 实用的提高效率的恒时异步分布式密钥生成

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-16 DOI: 10.1109/tifs.2025.3622362

Zhaoyang Xie, Haibin Zhang, Shengli Liu, Sisi Duan, Liehuang Zhu

引用次数: 0

Achieving Packet Traceback by Inferring AS-level Topology based on Cryptographic Path Identifiers 基于加密路径标识符的as级拓扑推断实现报文回溯

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-15 DOI: 10.1109/tifs.2025.3622069

Hongbin Luo, Hongyi Li, Shan Zhang, Yuxin Mao, Zhiyuan Wang

引用次数: 0

User-autonomous Multi-Factor Authentication Supporting Arbitrary Factor Configurations 支持任意因素配置的用户自治多因素认证

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-15 DOI: 10.1109/tifs.2025.3622084

Wenting Li, Haibo Cheng, Kaitai Liang

引用次数: 0

Posture-aware Robust Person Re-identification via Optimal Transport Calibration 基于最优运输校准的姿态感知鲁棒人再识别

IF 6.8 1区计算机科学

IEEE Transactions on Information Forensics and Security Pub Date : 2025-10-15 DOI: 10.1109/tifs.2025.3622067

Ruiying Lu, Yalin Sun, Chunlei Peng, Yu Zheng

引用次数: 0