5 papers
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
Yiwei Chen, Soumyadeep Pal, Yimeng Zhang +2
Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while…
The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models
Siyi Chen, Yimeng Zhang, Sijia Liu +1
Diffusion models excel at generating high-quality images but can memorize and reproduce harmful concepts when prompted. Although fine-tuning methods have been proposed to unlearn a…
ID-Patch: Robust ID Association for Group Photo Personalization
Yimeng Zhang, Tiancheng Zhi, Jing Liu +5
The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it p…
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
Yihua Zhang, Chongyu Fan, Yimeng Zhang +8
The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. Howev…
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Yimeng Zhang, Xin Chen, Jinghan Jia +6
Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyri…