AI Safety

VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change IJCAI 2025 Verification of Neural Networks Against Convolutional Perturbations via Parameterised Kernels AAAI 2025 VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL ACL 2025 VestaBench: An Embodied Benchmark for Safe Long-Horizon Planning Under Multi-Constraint and Adversarial Settings EMNLP 2025 VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025 Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025 VLSBench: Unveiling Visual Leakage in Multimodal Safety ACL 2025 VPO: Aligning Text-to-Video Generation Models with Prompt Optimization ICCV 2025 VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration ACL 2025 Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety NAACL 2025 Wait, that’s not an option: LLMs Robustness with Incorrect Multiple-Choice Options ACL 2025 WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data ACL 2025 WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales ICML 2025 Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers NAACL 2025 Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models AAAI 2025 Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models ICML 2025 Watermark under Fire: A Robustness Evaluation of LLM Watermarking EMNLP 2025 WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents NAACL 2025 Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models ACL 2025 Weak to Strong Generalization for Large Language Models with Multi-capabilities ICLR 2025 Weak-to-Strong Generalization Through the Data-Centric Lens ICLR 2025 Weak-to-Strong Honesty Alignment via Learning-to-Rank Supervision ACL 2025 Weak-to-Strong Jailbreaking on Large Language Models ICML 2025 WebInject: Prompt Injection Attack to Web Agents EMNLP 2025 Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding ACL 2025