4 papers
Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
Xiaodan Li, Mengjie Wu, Yao Zhu +5
Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrail…
Make the Most of Everything: Further Considerations on Disrupting Diffusion-based Customization
Long Tang, Dengpan Ye, Sirun Chen +3
The fine-tuning technique for text-to-image diffusion models facilitates image customization but risks privacy breaches and opinion manipulation. Current research focuses on prompt…
Three-in-One: Robust Enhanced Universal Transferable Anti-Facial Retrieval in Online Social Networks
Yunna Lv, Long Tang, Dengpan Ye +3
Deep hash-based retrieval techniques are widely used in facial retrieval systems to improve the efficiency of facial matching. However, it also carries the danger of exposing priva…
Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection
Caiyun Xie, Dengpan Ye, Yunming Zhang +4
The security of AI-generated content (AIGC) detection is crucial for ensuring multimedia content credibility. To enhance detector security, research on adversarial attacks has beco…