Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on adversarial attacks that introduce crafted perturbations to protect images from diffusion-based models. However, most existing approaches target image generation, while relatively few explicitly address image-to-video diffusion models (VDMs), and most primarily focus on UNet-based architectures. Hence, their effectiveness against Diffusion Transformer (DiT) models remains largely under-explored, as these models demonstrate improved feature retention, and stronger temporal consistency due to larger capacity and advanced attention mechanisms. In this work, we introduce Anti-I2V, a novel defense against malicious human image-to-video generation, applicable across diverse diffusion backbones. Instead of restricting noise updates to the RGB space, Anti-I2V operates in both the $L$*$a$*$b$* and frequency domains, improving robustness and concentrating on salient pixels. We then identify the network layers that capture the most distinct semantic features during the denoising process to design appropriate training objectives that maximize degradation of temporal coherence and generation fidelity. Through extensive validation, Anti-I2V demonstrates state-of-the-art defense performance against diverse video diffusion models, offering an effective solution to the problem.
Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);College of Electrical Engineering and the Ubiquitous System Security Lab (USSLab), Zhejiang University(浙江大学电子工程学院和无处不在系统安全实验室);ETH Zurich(苏黎世联邦理工学院)
Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
Faculty of Innovation Engineering(创新工程学院);Macau University of Science and Technology(澳门科学技术大学);School of Computer Science and Engineering(计算机科学与工程学院);University of Electronic Science and Technology of China(电子科技大学)
Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS)(人工智能安全国家重点实验室,计算技术研究所,中国科学院);University of China Academy of Sciences(中国科学院大学);Center for Machine Vision and Signal Analysis, University of Oulu(信号分析中心,奥卢大学);School of Computer Science, China University of Geosciences(计算机科学学院,中国地质大学)
A Dual-Branch CNN for Robust Detection of AI-Generated Facial Forgeries
Computer Science Department University of Southern Maine Portland, United States(计算机科学系 俄亥俄州立大学 帕斯托市 美国);The Department of Computer Science University of Central Oklahoma Edmond, United States(计算机科学系 中央俄克拉荷马大学 埃德蒙德 美国)
Synthetic Image Generation in Cyber Influence Operations: An Emergent Threat?
Institute for Data Science I4DS(数据科学研究所I4DS);University of Applied Sciences FHNW(FHNW应用科学大学);Cyber-Defence Campus(网络防御园区);armasuisse S+T(瑞士Armasuisse科技公司)
University of Waterloo(滑铁卢大学);University of Alberta(阿尔伯塔大学);National University of Singapore(新加坡国立大学);University of California, Merced(加利福尼亚大学默塞德分校);University at Buffalo, State University of New York(纽约州立大学布法罗分校);University of Queensland(昆士兰大学)
SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting
Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki(阿尔伯塔大学电气与计算机工程系);Information Technologies Institute, CERTH(信息科技研究所)