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

Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025
Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025
Multi-Turn Jailbreaking Large Language Models via Attention Shifting AAAI 2025
Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking CVPR 2025
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts AAAI 2025
Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models AAAI 2025
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates AAAI 2025
JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs AAAI 2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update AAAI 2025
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs ACL 2025
Safety in Large Reasoning Models: A Survey EMNLP 2025
Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions EMNLP 2025
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding EMNLP 2025
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency ICCV 2025
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks EMNLP 2025
Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025
Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region ACL 2025
SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs EMNLP 2025
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025
SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025