AI Safety

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs ICML 2025 Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies RSS 2025 Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models ACL 2025 Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems ICLR 2025 Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security Perspective ACL 2025 Can You Trick the Grader? Adversarial Persuasion of LLM Judges EMNLP 2025 CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement ACL 2025 CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models ICML 2025 Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions ACL 2025 CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations ACL 2025 CDI: Copyrighted Data Identification in Diffusion Models CVPR 2025 Certified Causal Defense with Generalizable Robustness AAAI 2025 Certified Human Trajectory Prediction CVPR 2025 Certified Mitigation of Worst-Case LLM Copyright Infringement EMNLP 2025 Certified Trustworthiness in the Era of Large Language Models AAAI 2025 Certifying Counterfactual Bias in LLMs ICLR 2025 Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks ICLR 2025 Chain of Attack: Hide Your Intention through Multi-Turn Interrogation ACL 2025 Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks CVPR 2025 Chain-of-Jailbreak Attack for Image Generation Models via Step by Step Editing ACL 2025 Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models ACL 2025 Challenges and Remedies of Domain-Specific Classifiers as LLM Guardrails: Self-Harm as a Case Study NAACL 2025 Challenges in Trustworthy Human Evaluation of Chatbots NAACL 2025 ChameleonBench: Quantifying Alignment Faking in Large Language Models ACML 2025 Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs EMNLP 2025