Stronger Universal and Transferable Attacks by Suppressing Refusals
Authors:
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 5850-5876
Abstract
David Huang, Avidan Shah, Alexandre Araujo, David Wagner, Chawin Sitawarin. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.Keywords
This publication has 11 references indexed in Scilit:
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Open Sesame! Universal Black-Box Jailbreaking of Large Language ModelsApplied Sciences, 2024
- Improving Alignment and Robustness with Circuit Breakers2024
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically2024
- Uncovering Safety Risks of Large Language Models through Concept Activation Vector2024
- How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs2024
- MART: Improving LLM Safety with Multi-round Automatic Red-Teaming2024
- Jailbroken: How Does LLM Safety Training Fail?2023
- PromptAttack: Prompt-Based Attack for Language Models via Gradient Search2022
- Universal Adversarial Triggers for Attacking and Analyzing NLP2019