AI Safety

EMNLP: Educator-role Moral and Normative Large Language Models Profiling EMNLP 2025 EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety EMNLP 2025 Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection ICML 2025 Encoding Values: Injecting Morality into Machines via Prompt-Conditioned Moral Frames NeurIPS 2025 Endless Jailbreaks with Bijection Learning ICLR 2025 English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025 Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability ICML 2025 Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training CVPR 2025 Enhancing LLM Agent Safety via Causal Influence Prompting ACL 2025 Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems ACL 2025 Enhancing the Adversarial Robustness via Manifold Projection AAAI 2025 Enhancing Transferability of Targeted Adversarial Examples via Inverse Target Gradient Competition and Spatial Distance Stretching ICCV 2025 Ensemble Watermarks for Large Language Models ACL 2025 ESF: Efficient Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models ACL 2025 Estimating the Probabilities of Rare Outputs in Language Models ICLR 2025 ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time ICLR 2025 Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective ACL 2025 Evaluating Large Language Models for Confidence-based Check Set Selection ACL 2025 Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study EMNLP 2025 Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Models ACL 2025 Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation ACL 2025 EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint EMNLP 2025 Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability AAAI 2025 Evolution of Aegis: Fault Diagnosis for AI Model Training Service in Production NSDI 2025 Exact Certification of (Graph) Neural Networks Against Label Poisoning ICLR 2025