Results 251 to 260 of about 4,729,114 (317)

WMamba: Wavelet-based Mamba for Face Forgery Detection

ACM Multimedia
The rapid evolution of deepfake generation technologies necessitates the development of robust face forgery detection algorithms. Recent studies have demonstrated that wavelet analysis can enhance the generalization abilities of forgery detectors ...
Siran Peng, Tianshuo Zhang, Li Gao, Xiangyu Zhu, Haoyuan Zhang, Kai Pang, Zhen Lei   +6 more
semanticscholar   +1 more source

MLLM-Enhanced Face Forgery Detection: A Vision-Language Fusion Solution

arXiv.org
Reliable face forgery detection algorithms are crucial for countering the growing threat of deepfake-driven disinformation. Previous research has demonstrated the potential of Multimodal Large Language Models (MLLMs) in identifying manipulated faces ...
Siran Peng, Zipei Wang, Li Gao, Xiangyu Zhu, Tianshuo Zhang, Ajian Liu, Haoyuan Zhang, Zhen Lei   +7 more
semanticscholar   +1 more source

Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models

Computer Vision and Pattern Recognition
Recently, the rapid development of AIGC has significantly boosted the diversities of fake media spread in the Internet, posing unprecedented threats to social security, politics, law, and etc.
Jin Wang, Chenghui Lv, Xian Li, Shichao Dong, Huadong Li, Kelu Yao, Chao Li, Wenqi Shao, Ping Luo   +8 more
semanticscholar   +1 more source

Toward Generalizable Forgery Detection and Reasoning

IEEE Transactions on Image Processing
Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models makes it challenging to develop a generalizable forgery detection model ...
Yueying Gao, Dongliang Chang, Bingyao Yu, Haotian Qin, Lei Chen, Kongming Liang, Zhanyu Ma   +6 more
semanticscholar   +1 more source

FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

International Conference on Learning Representations
The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect.
Zhipei Xu, Xuanyu Zhang, Runyi Li, Zecheng Tang, Qing Huang, Jian Zhang   +5 more
semanticscholar   +1 more source

LDFnet: Lightweight Dynamic Fusion Network for Face Forgery Detection by Integrating Local Artifacts and Global Texture Information

IEEE transactions on circuits and systems for video technology (Print)
Face forgery detection has become a new research hotspot. Though existing detection works have achieved impressive performance, they are difficult to achieve a proper trade-off between detection accuracy and model complexity.
Zhiqing Guo, Liejun Wang, Wenzhong Yang, Gaobo Yang, Keqin Li   +4 more
semanticscholar   +1 more source

Face Forgery Detection via Multi-Feature Fusion and Local Enhancement

IEEE transactions on circuits and systems for video technology (Print)
With the rapid growth of Internet technology, security concerns have risen, particularly with the prevalence of Deepfakes, a popular visual forgery technique. Therefore, there is necessary to research more powerful methods to detect Deepfakes.
Dengyong Zhang, Jiahao Chen, Xin Liao, Feng Li, Jiaxin Chen, Gaobo Yang   +5 more
semanticscholar   +1 more source

UCM-Net: A U-Net-Like Tampered-Region-Related Framework for Copy-Move Forgery Detection

IEEE transactions on multimedia
Copy-move forgery causes a big challenge to copy-move forgery detection (CMFD) due to that the photometrical characteristics of genuine and tampered regions in the same image remain highly consistent.
S. Weng, Tangguo Zhu, Tiancong Zhang, Chunyu Zhang   +3 more
semanticscholar   +1 more source

SHIELD: an evaluation benchmark for face spoofing and forgery detection with multimodal large language models

Visual Intelligence
Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks, capitalizing on their visual semantic comprehension and reasoning capabilities.
Yichen Shi, Yuhao Gao, Yingxin Lai, Hongyang Wang, Jun Feng, Lei He, Jun Wan, Changsheng Chen, Zitong Yu, Xiaochun Cao   +9 more
semanticscholar   +1 more source

MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection

IEEE Transactions on Dependable and Secure Computing
Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN-based face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance ...
Chenqi Kong, Anwei Luo, Peijun Bao, Yi Yu, Haoliang Li, Zengwei Zheng, Shiqi Wang, A. Kot   +7 more
semanticscholar   +1 more source