conftrace_

jailbreak attack

225 papers

Explore in graph

Co-occurring keywords

large language model (13587) adversarial attack (1621) safety alignment (178) adversarial learning (1595) prompt injection (101) ai safety (235) adversarial prompt (65) llm safety (67) model safety (101) prompt engineering (1135)

Papers

Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks EMNLP 2024
Jailbreak Open-Sourced Large Language Models via Enforced Decoding ACL 2024
Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models ACL 2024
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs ACL 2024
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs ACL 2024
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking NAACL 2024
Fake Alignment: Are LLMs Really Aligned Well? NAACL 2024
SELF-GUARD: Empower the LLM to Safeguard Itself NAACL 2024
Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks COLING 2024
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues ACL 2024
On the Vulnerability of Safety Alignment in Open-Access LLMs ACL 2024
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models ACL 2024
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails ACL 2024
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models NIPS 2024
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models EMNLP 2024
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis EMNLP 2024
ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings EMNLP 2024
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs NAACL 2024
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing NAACL 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding ACL 2024
ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages ACL 2024
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NIPS 2024
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses NIPS 2024
Jailbroken: How Does LLM Safety Training Fail? NIPS 2023