A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
Top Cited Papers
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 7432-7449
Abstract
Zihao Xu, Yi Liu, Gelei Deng, Yuekang Li, Stjepan Picek. Findings of the Association for Computational Linguistics ACL 2024. 2024.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Jatmo: Prompt Injection Defense by Task-Specific Finetuning2024
- Open Sesame! Universal Black-Box Jailbreaking of Large Language ModelsApplied Sciences, 2024
- Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks2024
- FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models2024
- Preference Ranking Optimization for Human AlignmentProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM2024