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

Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs AAAI 2026

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation ACL 2026

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models EACL 2026

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models AAAI 2026

MacPrompt: Maraconic-Guided Jailbreak Against Text-to-Image Models AAAI 2026

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning ACL 2026

Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models EACL 2026

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage EACL 2026

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization EACL 2026

MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies AAAI 2026

Unveiling AI Safety in Fine-tuning Quantized Model AAAI 2026

Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning AAAI 2026

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion AAAI 2026

MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs AAAI 2026

Unraveling LLM Jailbreaks Through Safety Knowledge Neurons EACL 2026

Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models EACL 2026

Safeguarding Language Models via Self-Destruct Trapdoor EACL 2026

Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations EACL 2026

A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking EACL 2026

Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models AAAI 2026

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity AAAI 2026

AlignTree: Efficient Defense Against LLM Jailbreak Attacks AAAI 2026

Always Refuse: Steering LLMs Against Jailbreaks with Contrastive Activations (Student Abstract) AAAI 2026

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification ACL 2026