← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

On the Utility of Lay Summaries and AI Safety Disclosures: Toward Robust, Open Research Oversight NAACL 2018
Efficient Formal Safety Analysis of Neural Networks NIPS 2018
A Lyapunov-based Approach to Safe Reinforcement Learning NIPS 2018
Improved Network Robustness with Adversary Critic NIPS 2018
Constrained Cross-Entropy Method for Safe Reinforcement Learning NIPS 2018
Fast and Effective Robustness Certification NIPS 2018
Lipschitz regularity of deep neural networks: analysis and efficient estimation NIPS 2018
Efficient Neural Network Robustness Certification with General Activation Functions NIPS 2018
Adversarial vulnerability for any classifier NIPS 2018
Probabilistically Safe Robot Planning with Confidence-Based Human Predictions RSS 2018
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks NIPS 2018
Learning to Solve SMT Formulas NIPS 2018
Online Learning with an Unknown Fairness Metric NIPS 2018
Semidefinite relaxations for certifying robustness to adversarial examples NIPS 2018
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks NIPS 2018
Predictive Uncertainty Estimation via Prior Networks NIPS 2018
Artificial Argumentation for Humans IJCAI 2018
Hatebusters: A Web Application for Actively Reporting YouTube Hate Speech IJCAI 2018
Probabilistic Verification for Obviously Strategyproof Mechanisms IJCAI 2018
Learning Safe Policies with Expert Guidance NIPS 2018
Inverse Reward Design NIPS 2017
The Off-Switch Game IJCAI 2017
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation NIPS 2017
Lower bounds on the robustness to adversarial perturbations NIPS 2017
Generalizing GANs: A Turing Perspective NIPS 2017