# yuplin2333/representation-space-jailbreak

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/yuplin2333-representation-space-jailbreak).**

24 stars · 2 forks · Python · MIT

## Links

- GitHub: https://github.com/yuplin2333/representation-space-jailbreak
- awesome-repositories: https://awesome-repositories.com/repository/yuplin2333-representation-space-jailbreak.md

## Description

This repo contains the code used in our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis. (arXiv)

## Tags

### Part of an Awesome List

- [Evaluation Benchmarks](https://awesome-repositories.com/f/awesome-lists/ai/evaluation-benchmarks.md) — Analyzes jailbreak attacks through model representation spaces.
