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

The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs ACL 2025
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming ACL 2025
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks EMNLP 2025
Understanding Refusal in Language Models with Sparse Autoencoders EMNLP 2025
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs EMNLP 2025
Multi-Turn Jailbreaking Large Language Models via Attention Shifting AAAI 2025
Safety in Large Reasoning Models: A Survey EMNLP 2025
What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs ACL 2025
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts? EMNLP 2025
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization ACL 2025
Jailbreaking? One Step Is Enough! ACL 2025
HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States ACL 2025
Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region ACL 2025
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs ACL 2025
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025
Safety Alignment via Constrained Knowledge Unlearning ACL 2025
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges ACL 2025
Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization IJCNLP 2025
Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety NAACL 2025
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response NAACL 2025
Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models NAACL 2025
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs NAACL 2025
Tongue-Tied: Breaking LLMs Safety Through New Language Learning NAACL 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025