Attention Shift: Steering AI Away from Unsafe Content

Abstract

This study investigates the generation of unsafe or harmful content in state-of-the-art generative models, focusing on methods for restricting such generations. We introduce a novel training-free approach using attention reweighing to remove unsafe concepts without additional training during inference. We compare our method against existing ablation methods, evaluating the performance on both, direct and adversarial jailbreak prompts, using qualitative and quantitative metrics. We hypothesize potential reasons for the observed results and discuss the limitations and broader implications of content restriction.