AI Safety

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection NAACL 2025 from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors ACL 2025 From End-Users to Co-Designers: Lessons from Teachers ACL 2025 From Gambits to Assurances: Game-Theoretic Integration of Safety and Learning for Interactive Robotics AAAI 2025 From Imitation to Introspection: Probing Self-Consciousness in Language Models ACL 2025 From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment ACL 2025 From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs? EMNLP 2025 From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting CoRL 2025 Fundamental Limits of Membership Inference Attacks on Machine Learning Models JMLR 2025 Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation AAAI 2025 G2LDetect: A Global-to-Local Approach for Hallucination Detection AAAI 2025 Gandalf the Red: Adaptive Security for LLMs ICML 2025 General agents need world models ICML 2025 Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis RSS 2025 General Uncertainty Estimation with Delta Variances AAAI 2025 Generating Robot Constitutions & Benchmarks for Semantic Safety CoRL 2025 Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models ACL 2025 GeoSAFE - A Novel Geospatial Artificial Intelligence Safety Assurance Framework and Evaluation for LLM Moderation IJCNLP 2025 GIL-IIMAS UNAM at SemEval-2025 Task 4: LA-Min(E): LLM Unlearning Approaches Under Function Minimizing Evaluation Constraints SemEval 2025 GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization AAAI 2025 Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection ICLR 2025 Goal-Conditioned DPO: Prioritizing Safety in Misaligned Instructions NAACL 2025 GOODLIAR: A Reinforcement Learning-Based Deceptive Agent for Disrupting LLM Beliefs on Foundational Principles ACL 2025 Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety EMNLP 2025 GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks ICLR 2025