AI Safety

ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models CVPR 2025 One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs ICLR 2025 One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models ICCV 2025 One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems EMNLP 2025 On Evaluating the Durability of Safeguards for Open-Weight LLMs ICLR 2025 On Guardrail Models’ Robustness to Mutations and Adversarial Attacks EMNLP 2025 Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization IJCNLP 2025 Online Learning with Unknown Constraints ICML 2025 On Localizing and Deleting Toxic Memories in Large Language Models NAACL 2025 On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback ICLR 2025 On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning ICLR 2025 On the Adversarial Vulnerability of Label-Free Test-Time Adaptation ICLR 2025 On the Consideration of AI Openness: Can Good Intent Be Abused? AAAI 2025 On the Convergence of Moral Self-Correction in Large Language Models IJCNLP 2025 On the Robustness of Distributed Machine Learning Against Transfer Attacks AAAI 2025 On the Robustness Tradeoff in Fine-Tuning ICCV 2025 On the Role of Attention Heads in Large Language Model Safety ICLR 2025 On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs EMNLP 2025 On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains ICML 2025 On Weaponization-Resistant Large Language Models with Prospect Theoretic Alignment COLING 2025 Operationalising Rawlsian Ethics for Fairness in Norm Learning Agents AAAI 2025 Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work ACL 2025 Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach ICML 2025 OR-Bench: An Over-Refusal Benchmark for Large Language Models ICML 2025 Oversight Structures for Agentic AI in Public-Sector Organizations ACL 2025