← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Random Noise Defense Against Query-Based Black-Box Attacks NIPS 2021
Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods NIPS 2021
EarFisher: Detecting Wireless Eavesdroppers by Stimulating and Sensing Memory EMR NSDI 2021
Generating High-Quality Explanations for Navigation in Partially-Revealed Environments NIPS 2021
Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork AAAI 2021
Ethically Compliant Sequential Decision Making AAAI 2021
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks JMLR 2021
The Translucent Patch: A Physical and Universal Attack on Object Detectors CVPR 2021
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models AAAI 2021
Towards a Unifying Framework for Formal Theories of Novelty AAAI 2021
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning NIPS 2021
Adversarial Attacks on Graph Classifiers via Bayesian Optimisation NIPS 2021
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks NIPS 2021
Shift Invariance Can Reduce Adversarial Robustness NIPS 2021
Rethinking Stealthiness of Backdoor Attack against NLP Models ACL 2021
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models EMNLP 2021
Adversarial Robustness with Non-uniform Perturbations NIPS 2021
A PAC-Bayes Analysis of Adversarial Robustness NIPS 2021
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks NIPS 2021
Robustness of Graph Neural Networks at Scale NIPS 2021
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes NIPS 2021
Foundations of Symbolic Languages for Model Interpretability NIPS 2021
Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks L4DC 2021
Safe Bayesian Optimisation for Controller Design by Utilising the Parameter Space Approach L4DC 2021
Learning Approximate Forward Reachable Sets Using Separating Kernels L4DC 2021