conftrace_

jailbreaking attack

33 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (22) adversarial attack (9) model safety (7) safety alignment (6) adversarial prompt (5) prompt optimization (3) red teaming (3) prompt injection (3) adversarial prompting (3) multimodal large language model (3)

Papers

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content ICML 2024 Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks NeurIPS 2024 Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield NAACL 2024 Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models ICML 2024 SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation EMNLP 2024 Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NeurIPS 2024 When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search NeurIPS 2024 Multi-step Jailbreaking Privacy Attacks on ChatGPT EMNLP 2023