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

Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025
Tongue-Tied: Breaking LLMs Safety Through New Language Learning NAACL 2025
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language ACL 2025
Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement ACL 2025
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking? ACL 2025
SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025
Speculative Safety-Aware Decoding EMNLP 2025
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs NAACL 2025
Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models NAACL 2025
LlmFixer: Fix the Helpfulness of Defensive Large Language Models EMNLP 2025
Beneath the Facade: Probing Safety Vulnerabilities in LLMs via Auto-Generated Jailbreak Prompts EMNLP 2025
Reimagining Safety Alignment with An Image EMNLP 2025
Jailbreaking? One Step Is Enough! ACL 2025
Jailbreak Attack Initializations as Extractors of Compliance Directions EMNLP 2025
Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models EMNLP 2025
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025
Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy CVPR 2025
SLADE: Shielding against Dual Exploits in Large Vision-Language Models CVPR 2025
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment CVPR 2025
Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization AACL 2025
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing AACL 2025
Beyond Guardrails: Advanced Safety for Large Language Models — Monolingual, Multilingual and Multimodal Frontiers IJCNLP 2025
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025