6 papers
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…
OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
Adam Bawatneh, Sagar Sapkota, Amrit Singh Bedi +2
Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, wh…
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…
MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models
Kevin Zhai, Utsav Singh, Anirudh Thatipelli +5
Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aes…
Leveraging Pre-Trained Visual Models for AI-Generated Video Detection
Keerthi Veeramachaneni, Praveen Tirupattur, Amrit Singh Bedi +1
Recent advances in Generative AI (GenAI) have led to significant improvements in the quality of generated visual content. As AI-generated visual content becomes increasingly indist…
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…