conftrace_

prompt injection

107 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (63) adversarial attack (46) jailbreak attack (28) adversarial learning (13) adversarial prompt (11) llm security (9) security vulnerability (7) security evaluation (7) language model (7) model safety (7)

Papers

SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases EMNLP 2024 Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks COLING 2024 Uncovering Safety Risks of Large Language Models through Concept Activation Vector NeurIPS 2024 WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models EMNLP 2024 Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition EMNLP 2023 Multi-step Jailbreaking Privacy Attacks on ChatGPT EMNLP 2023 TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models NeurIPS 2023