conftrace_

safety alignment

178 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) adversarial attack (1621) model safety (101) harmful content (66) multimodal large language model (966) ai safety (235) language model (4599) llm safety (67) adversarial learning (1595)

Papers

Don’t Say No: Jailbreaking LLM by Suppressing Refusal ACL 2025
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025
sudoLLM: On Multi-role Alignment of Language Models EMNLP 2025
Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs EMNLP 2025
MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models AAAI 2025
VLSBench: Unveiling Visual Leakage in Multimodal Safety ACL 2025
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs ACL 2025
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis ACL 2025
Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region ACL 2025
MPO: Multilingual Safety Alignment via Reward Gap Optimization ACL 2025
Representation Bending for Large Language Model Safety ACL 2025
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings ACL 2025
Safety Alignment via Constrained Knowledge Unlearning ACL 2025
SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion ACL 2025
Large Language Models Encode Semantics and Alignment in Linearly Separable Representations IJCNLP 2025
Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Models NAACL 2025
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response NAACL 2025
Smaller Large Language Models Can Do Moral Self-Correction NAACL 2025
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refine NAACL 2025
LongSafety: Enhance Safety for Long-Context LLMs ACL 2025
Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency ACL 2025
SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models EMNLP 2025
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025
Reimagining Safety Alignment with An Image EMNLP 2025