AI Safety

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems ICML 2025 Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings ACL 2025 CRAFT: Class Ranking Aware Fine-Tuning for Enhanced Out-of-Distribution Detection WACV 2025 CREAM: Consistency Regularized Self-Rewarding Language Models ICLR 2025 Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks AAAI 2025 Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models ICLR 2025 CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization ICML 2025 Cultural Learning-Based Culture Adaptation of Language Models ACL 2025 CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications IJCNLP 2025 Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation EMNLP 2025 Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems ICLR 2025 Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025 Dagger Behind Smile: Fool LLMs with a Happy Ending Story EMNLP 2025 DAMAGE: Detecting Adversarially Modified AI Generated Text COLING 2025 DAMAGeR: Deploying Automatic and Manual Approaches to GenAI Red-teaming NAACL 2025 DAMON: A Dialogue-Aware MCTS Framework for Jailbreaking Large Language Models EMNLP 2025 Data Poisoning for In-context Learning NAACL 2025 Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise EMNLP 2025 Data with High and Consistent Preference Difference Are Better for Reward Model AAAI 2025 DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing ICCV 2025 DeAL: Decoding-time Alignment for Large Language Models ACL 2025 Debate Helps Weak-to-Strong Generalization AAAI 2025 Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal CVPR 2025 Decoding Hate: Exploring Language Models’ Reactions to Hate Speech NAACL 2025 Decoupling Metacognition from Cognition: A Framework for Quantifying Metacognitive Ability in LLMs AAAI 2025