AI Safety

Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability L4DC 2020 DBA: Distributed Backdoor Attacks against Federated Learning ICLR 2020 Deception through Half-Truths AAAI 2020 Defending Against Model Stealing Attacks With Adaptive Misinformation CVPR 2020 Defense Through Diverse Directions ICML 2020 (De)Randomized Smoothing for Certifiable Defense against Patch Attacks NeurIPS 2020 Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error IJCAI 2020 Detection as Regression: Certified Object Detection with Median Smoothing NeurIPS 2020 Diagnosing Software Faults Using Multiverse Analysis IJCAI 2020 Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning COLING 2020 Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization NeurIPS 2020 Efficient Proximal Mapping of the 1-path-norm of Shallow Networks ICML 2020 Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More ICML 2020 Efficient Verification of ReLU-Based Neural Networks via Dependency Analysis AAAI 2020 Enhancing Adversarial Defense by k-Winners-Take-All ICLR 2020 Fastened CROWN: Tightened Neural Network Robustness Certificates AAAI 2020 FastLAS: Scalable Inductive Logic Programming Incorporating Domain-Specific Optimisation Criteria AAAI 2020 Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents ICLR 2020 Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations ICML 2020 Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data CVPR 2020 Generating Adversarial Examples for Holding Robustness of Source Code Processing Models AAAI 2020 Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis? ACL 2020 GNNGuard: Defending Graph Neural Networks against Adversarial Attacks NeurIPS 2020 GreedyFool: Distortion-Aware Sparse Adversarial Attack NeurIPS 2020 Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions CoRL 2020