← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Safety Analysis of Deep Neural Networks IJCAI 2021
Thinking Fast and Slow in AI AAAI 2021
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee ICML 2021
Value Alignment Verification ICML 2021
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution ACL 2021
Verifying Reinforcement Learning up to Infinity IJCAI 2021
Multi-Objective Reinforcement Learning for Designing Ethical Environments IJCAI 2021
Density Constrained Reinforcement Learning ICML 2021
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models NAACL 2021
Certified Robustness to Word Substitution Attack with Differential Privacy NAACL 2021
Concealed Data Poisoning Attacks on NLP Models NAACL 2021
Provably Safe PAC-MDP Exploration Using Analogies AISTATS 2021
Hidden Cost of Randomized Smoothing AISTATS 2021
Bayesian Inference with Certifiable Adversarial Robustness AISTATS 2021
Detection and Defense of Topological Adversarial Attacks on Graphs AISTATS 2021
Robust and Private Learning of Halfspaces AISTATS 2021
The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity IJCNLP 2021
Reliability Testing for Natural Language Processing Systems IJCNLP 2021
Rethinking Stealthiness of Backdoor Attack against NLP Models IJCNLP 2021
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution IJCNLP 2021
Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning RSS 2021
Lyapunov-stable neural-network control RSS 2021
A Law of Robustness for Two-Layers Neural Networks COLT 2021
Certification of iterative predictions in Bayesian neural networks UAI 2021
Formal verification of neural networks for safety-critical tasks in deep reinforcement learning UAI 2021