AI Safety

Computational Limitations in Robust Classification and Win-Win Results COLT 2019 Counter-example Guided Learning of Bounds on Environment Behavior CoRL 2019 DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks IJCAI 2019 Deep Learning without Weight Transport NeurIPS 2019 Defending Against Adversarial Attacks by Randomized Diversification CVPR 2019 Defending Against Neural Fake News NeurIPS 2019 Defending against Whitebox Adversarial Attacks via Randomized Discretization AISTATS 2019 Designing Preferences, Beliefs, and Identities for Artificial Intelligence AAAI 2019 Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View CVPR 2019 DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense ICCV 2019 End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks AAAI 2019 Enhancing Adversarial Example Transferability With an Intermediate Level Attack ICCV 2019 Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks CVPR 2019 Evaluating Robustness of Neural Networks with Mixed Integer Programming ICLR 2019 Explainable, Normative, and Justified Agency AAAI 2019 Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation ICML 2019 From Data to Knowledge Engineering for Cybersecurity IJCAI 2019 Generating 3D Adversarial Point Clouds CVPR 2019 Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the Hamming Distance IJCAI 2019 Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour IJCAI 2019 Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness IJCAI 2019 How do we feel when a robot dies? Emotions expressed on Twitter before and after hitchBOT’s destruction NAACL 2019 Identifying vulnerabilities in trust and reputation systems IJCAI 2019 Interpretation of Neural Networks Is Fragile AAAI 2019 Interpreting and Evaluating Neural Network Robustness IJCAI 2019