3 papers
cs.CV2026
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Adeel Yousaf, Soumik Ghosh, James Beetham +2
Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver hig…
cs.CV2025
SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
Adeel Yousaf, Joseph Fioresi, James Beetham +2
Improving the safety of vision-language models like CLIP via fine-tuning often comes at a steep price, causing significant drops in their generalization performance. We find this t…
cs.CL2025
LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
James Beetham, Souradip Chakraborty, Mengdi Wang +3
Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or tr…