← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

CerDEQ: Certifiable Deep Equilibrium Model ICML 2022
Double Sampling Randomized Smoothing ICML 2022
Diffusion Models for Adversarial Purification ICML 2022
A Causal Analysis of Harm NIPS 2022
ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation EMNLP 2022
Adversarial training for high-stakes reliability NIPS 2022
Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models NIPS 2022
Safe Robot Learning in Assistive Devices through Neural Network Repair CORL 2022
Safe Control Under Input Limits with Neural Control Barrier Functions CORL 2022
A Model Selection Approach for Corruption Robust Reinforcement Learning ALT 2022
Measuring Data Reconstruction Defenses in Collaborative Inference Systems NIPS 2022
Regret Bounds for Risk-Sensitive Reinforcement Learning NIPS 2022
Enhancing Safe Exploration Using Safety State Augmentation NIPS 2022
Parametrically Retargetable Decision-Makers Tend To Seek Power NIPS 2022
Provable Defense against Backdoor Policies in Reinforcement Learning NIPS 2022
Shield Decentralization for Safe Multi-Agent Reinforcement Learning NIPS 2022
Threat Scenarios and Best Practices to Detect Neural Fake News COLING 2022
Are AlphaZero-like Agents Robust to Adversarial Perturbations? NIPS 2022
Defining and Characterizing Reward Gaming NIPS 2022
Constrained Update Projection Approach to Safe Policy Optimization NIPS 2022
Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity NIPS 2022
On the Limitations of Stochastic Pre-processing Defenses NIPS 2022
Information-Theoretic Safe Exploration with Gaussian Processes NIPS 2022
When are Local Queries Useful for Robust Learning? NIPS 2022
Improving Certified Robustness via Statistical Learning with Logical Reasoning NIPS 2022