← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms NIPS 2023
BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset NIPS 2023
Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark NIPS 2023
Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning NIPS 2023
Learning Shared Safety Constraints from Multi-task Demonstrations NIPS 2023
Language Model Alignment with Elastic Reset NIPS 2023
Honesty Is the Best Policy: Defining and Mitigating AI Deception NIPS 2023
Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning NIPS 2023
Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation NIPS 2023
Red Teaming Deep Neural Networks with Feature Synthesis Tools NIPS 2023
Provably Bounding Neural Network Preimages NIPS 2023
Connecting Certified and Adversarial Training NIPS 2023
Multi-scale Diffusion Denoised Smoothing NIPS 2023
CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches NIPS 2023
FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning NIPS 2023
Enhancing Adversarial Robustness via Score-Based Optimization NIPS 2023
Optimizing over trained GNNs via symmetry breaking NIPS 2023
Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly NIPS 2023
Improving Robustness with Adaptive Weight Decay NIPS 2023
Static and Sequential Malicious Attacks in the Context of Selective Forgetting NIPS 2023
Robust Bayesian Satisficing NIPS 2023
Black-box Backdoor Defense via Zero-shot Image Purification NIPS 2023
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks NIPS 2023
Certification of Distributional Individual Fairness NIPS 2023
Attacks on Online Learners: a Teacher-Student Analysis NIPS 2023