4 papers
Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models
Yaoteng Tan, Zikui Cai, M. Salman Asif
Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated…
Cross-Modal Safety Alignment: Is textual unlearning all you need?
Trishna Chakraborty, Erfan Shayegani, Zikui Cai +5
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing…
Targeted Unlearning with Single Layer Unlearning Gradient
Zikui Cai, Yaoteng Tan, M. Salman Asif
Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while pot…
Transform-Dependent Adversarial Attacks
Yaoteng Tan, Zikui Cai, M. Salman Asif
Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work,…