AI Safety

VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models CVPR 2024 Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack NeurIPS 2024 Validating the eBPF Verifier via State Embedding OSDI 2024 Value Alignment from Unstructured Text EMNLP 2024 ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models ACL 2024 Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value NAACL 2024 Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation CoRL 2024 Verification of neural reachable tubes via scenario optimization and conformal prediction L4DC 2024 Verified Safe Reinforcement Learning for Neural Network Dynamic Models NeurIPS 2024 Virtual Context Enhancing Jailbreak Attacks with Special Token Injection EMNLP 2024 Visual Adversarial Examples Jailbreak Aligned Large Language Models AAAI 2024 VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees ICML 2024 Vulnerabilities of Large Language Models to Adversarial Attacks ACL 2024 WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models EMNLP 2024 Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents NeurIPS 2024 Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models CVPR 2024 Watermarking Makes Language Models Radioactive NeurIPS 2024 Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models ICML 2024 WatME: Towards Lossless Watermarking Through Lexical Redundancy ACL 2024 WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks NeurIPS 2024 Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision ICML 2024 Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models NeurIPS 2024 WebOlympus: An Open Platform for Web Agents on Live Websites EMNLP 2024 WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions EMNLP 2024 What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning IJCAI 2024