conftrace_

adversarial prompt

65 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) adversarial attack (1621) red teaming (61) prompt injection (101) prompt engineering (1135) language model (4599) text-to-image model (157) safety alignment (178) adversarial learning (1595)

Papers

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming NAACL 2024
Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield NAACL 2024
PromptBench: A Unified Library for Evaluation of Large Language Models JMLR 2024
Prompts have evil twins EMNLP 2024
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NIPS 2024
On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning AAAI 2024
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs ACL 2024
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs ACL 2024
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing EMNLP 2024
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts NIPS 2024
GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation EMNLP 2024
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification ACL 2024
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition EMNLP 2023
Attack Prompt Generation for Red Teaming and Defending Large Language Models EMNLP 2023
ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models EMNLP 2023