AI Safety

Inverse Reinforcement Learning Meets Large Language Model Alignment ACL 2025 InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes Under Herd Behavior ACL 2025 Investigating How Pre-training Data Leakage Affects Models’ Reproduction and Detection Capabilities EMNLP 2025 Investigating Motivated Inference in Large Language Models EMNLP 2025 Investigating the Security Threat Arising from “Yes-No” Implicit Bias in Large Language Models AAAI 2025 Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking EMNLP 2025 Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models EMNLP 2025 IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents EMNLP 2025 IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities ICLR 2025 Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment ICML 2025 Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models EMNLP 2025 Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body CVPR 2025 Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception AAAI 2025 Is Your Multimodal Language Model Oversensitive to Safe Queries? ICLR 2025 Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning ICLR 2025 Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities NAACL 2025 “I understand your perspective”: LLM Persuasion through the Lens of Communicative Action Theory ACL 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models ICLR 2025 Jailbreak Attack Initializations as Extractors of Compliance Directions EMNLP 2025 Jailbreak Defense in LLM via Attention Head Analysis and Selective Intervention ACML 2025 JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models ICCV 2025 Jailbreak Distillation: Renewable Safety Benchmarking EMNLP 2025 Jailbreaking as a Reward Misspecification Problem ICLR 2025 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks ICLR 2025