# Attention Shift: Steering AI Away from Unsafe Content

arXiv: https://arxiv.org/abs/2410.04447 · HTML: https://mlsanity.com/paper/2410.04447/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 6 Oct 2024.

## Placed in

- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications](https://mlsanity.com/paper/2312.16145/) (2023)
- [Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers](https://mlsanity.com/paper/2311.17717/) (2023)
- [Erasing Undesirable Influence in Diffusion Models](https://mlsanity.com/paper/2401.05779/) (2024)
- [Stable Diffusion Exposed: Gender Bias from Prompt to Image](https://mlsanity.com/paper/2312.03027/) (2023)
- [FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models](https://mlsanity.com/paper/2405.17814/) (2024)
- [Bias in Generative AI](https://mlsanity.com/paper/2403.02726/) (2024)
- [BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models](https://mlsanity.com/paper/2407.15240/) (2024)
- [Unmasking the Veil: An Investigation into Concept Ablation for Privacy and Copyright Protection in Images](https://mlsanity.com/paper/2406.12592/) (2024)

## Abstract (arXiv)

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.