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

Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency ICCV 2025
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025
Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025
Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025
QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety ACL 2025
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters NAACL 2025
SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring NAACL 2025
SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025
TombRaider: Entering the Vault of History to Jailbreak Large Language Models EMNLP 2025
VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025
SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models EMNLP 2025
Reimagining Safety Alignment with An Image EMNLP 2025
Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models EMNLP 2025
Speculative Safety-Aware Decoding EMNLP 2025
SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025
Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025
SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025
SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs EMNLP 2025
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks EMNLP 2025
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding EMNLP 2025
Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions EMNLP 2025