Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Data-Free Hard-Label Robustness Stealing Attack AAAI 2024

Negative Human Rights as a Basis for Long-term AI Safety and Regulation (Abstract Reprint) IJCAI 2024

Towards safe multi-task Bayesian optimization L4DC 2024

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections NAACL 2024

Towards the Robustness of Differentially Private Federated Learning AAAI 2024

SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures INTERSPEECH 2024

Backward Responsibility in Transition Systems Using General Power Indices AAAI 2024

Interactive Theorem Provers: Applications in AI, Opportunities, and Challenges AAAI 2024

Fostering Trustworthiness in Machine Learning Algorithms AAAI 2024

Adaptive Experiment Design with Synthetic Controls AISTATS 2024

Verification of neural reachable tubes via scenario optimization and conformal prediction L4DC 2024

Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions AISTATS 2024

Taming False Positives in Out-of-Distribution Detection with Human Feedback AISTATS 2024

Gradient shaping for multi-constraint safe reinforcement learning L4DC 2024

Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner EMNLP 2024

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NIPS 2024

Reward Penalties on Augmented States for Solving Richly Constrained RL Effectively AAAI 2024

Responsibility in Extensive Form Games AAAI 2024

Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming AAAI 2024

P2BPO: Permeable Penalty Barrier-Based Policy Optimization for Safe RL AAAI 2024

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation AAAI 2024

Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis AAAI 2024

Reward Certification for Policy Smoothed Reinforcement Learning AAAI 2024

Pure-Past Action Masking AAAI 2024

Long-Term Safe Reinforcement Learning with Binary Feedback AAAI 2024