conftrace_

jailbreak

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

llms (4) large language model (3) alignment (2) adversarial prompting (2) ai safety (2) toxicity (1) utility (1) guardrails (1) vulnerabilities (1) cold-attack (1)

Papers

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester ICML 2025 FlipAttack: Jailbreak LLMs via Flipping ICML 2025 Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI ICML 2025 Scaling Trends in Language Model Robustness ICML 2025 Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions ICML 2025 The Jailbreak Tax: How Useful are Your Jailbreak Outputs? ICML 2025 A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity ICML 2024 COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability ICML 2024 Fast Adversarial Attacks on Language Models In One GPU Minute ICML 2024 Fundamental Limitations of Alignment in Large Language Models ICML 2024 PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition ICML 2024