AI Safety

Removing RLHF Protections in GPT-4 via Fine-Tuning NAACL 2024 Representation Noising: A Defence Mechanism Against Harmful Finetuning NeurIPS 2024 Representation Surgery: Theory and Practice of Affine Steering ICML 2024 Responsibility in Extensive Form Games AAAI 2024 Rethinking Adversarial Robustness in the Context of the Right to be Forgotten ICML 2024 Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective ICLR 2024 Rethinking Machine Ethics – Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? NAACL 2024 Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond AAAI 2024 Reward Certification for Policy Smoothed Reinforcement Learning AAAI 2024 Reward Model Ensembles Help Mitigate Overoptimization ICLR 2024 Reward Penalties on Augmented States for Solving Richly Constrained RL Effectively AAAI 2024 RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content ICML 2024 RISE: Robust Early-exiting Internal Classifiers for Suicide Risk Evaluation COLING 2024 Risk-Averse Fine-tuning of Large Language Models NeurIPS 2024 Risk Aware Benchmarking of Large Language Models ICML 2024 Risk-Sensitive Reward-Free Reinforcement Learning with CVaR ICML 2024 R-Judge: Benchmarking Safety Risk Awareness for LLM Agents EMNLP 2024 RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment ICLR 2024 RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models ACL 2024 RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback CVPR 2024 Robust Inverse Constrained Reinforcement Learning under Model Misspecification ICML 2024 Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks ICLR 2024 Robustness Verification of Multi-Class Tree Ensembles AAAI 2024 Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks NeurIPS 2024 Robust Reinforcement Learning from Corrupted Human Feedback NeurIPS 2024