Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
Authors:
- Lang GaoLGLang Gao
- Jiahui GengJGJiahui Geng
- Xiangliang ZhangXZXiangliang Zhang
- Preslav NakovPNPreslav Nakov
- Xiuying ChenXCXiuying Chen
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 25378-25398
Abstract
Lang Gao, Jiahui Geng, Xiangliang Zhang, Preslav Nakov, Xiuying Chen. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Unveiling the power of language models in chemical research question answeringCommunications Chemistry, 2025
- "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models2024
- SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding2024
- ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs2024
- GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis2024
- Defending ChatGPT against jailbreak attack via self-remindersNature Machine Intelligence, 2023
- Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE)Computer Science Review, 2021
- A Taxonomy of Global Optimization Methods Based on Response SurfacesJournal of Global Optimization, 2001
- Divergence measures based on the Shannon entropyIEEE Transactions on Information Theory, 1991