AI Safety

Trustworthy Actionable Perturbations ICML 2024 Truthful High Dimensional Sparse Linear Regression NeurIPS 2024 TU Wien at SemEval-2024 Task 6: Unifying Model-Agnostic and Model-Aware Techniques for Hallucination Detection SemEval 2024 Twice Class Bias Correction for Imbalanced Semi-supervised Learning AAAI 2024 Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors NAACL 2024 ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average EMNLP 2024 Unbiased Watermark for Large Language Models ICLR 2024 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NeurIPS 2024 Uncovering Safety Risks of Large Language Models through Concept Activation Vector NeurIPS 2024 Understanding Certified Training with Interval Bound Propagation ICLR 2024 Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation ICLR 2024 Understanding the Learning Dynamics of Alignment with Human Feedback ICML 2024 Undetectable Watermarks for Language Models COLT 2024 Unelicitable Backdoors via Cryptographic Transformer Circuits NeurIPS 2024 Universal Jailbreak Backdoors from Poisoned Human Feedback ICLR 2024 Universal Prompt Optimizer for Safe Text-to-Image Generation NAACL 2024 Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning EMNLP 2024 UNIWIZ: A Unified Large Language Model Orchestrated Wizard for Safe Knowledge Grounded Conversations ACL 2024 Unlearning Traces the Influential Training Data of Language Models ACL 2024 Unsegment Anything by Simulating Deformation CVPR 2024 Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness NeurIPS 2024 Unveiling Privacy, Memorization, and Input Curvature Links ICML 2024 Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models NeurIPS 2024 UOR: Universal Backdoor Attacks on Pre-trained Language Models ACL 2024 U-trustworthy Models. Reliability, Competence, and Confidence in Decision-Making AAAI 2024