aaai 2020 论文列表Proceedings of the Workshop on Artificial Intelligence Safety, co-located with 34th AAAI Conference on Artificial Intelligence, SafeAI@AAAI 2020, New York City, NY, USA, February 7, 2020. |
Toward Operational Safety Verification Via Hybrid Automata Mining Using I/O Traces of AI-Enabled CPS.
Recurrent Neural Network Properties and their Verification with Monte Carlo Techniques.
Continuous Safe Learning Based on First Principles and Constraints for Autonomous Driving.
Practical Solutions for Machine Learning Safety in Autonomous Vehicles.
Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints.
Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometrics.
NewsBag: A Benchmark Multimodal Dataset for Fake News Detection.
(When) Is Truth-telling Favored in AI Debate?
SafeLife 1.0: Exploring Side Effects in Complex Environments.
Out-of-Distribution Detection with Likelihoods Assigned by Deep Generative Models Using Multimodal Prior Distributions.
Fair Representation for Safe Artificial Intelligence via Adversarial Learning of Unbiased Information Bottleneck.
Simple Continual Learning Strategies for Safer Classifers.
PURSS: Towards Perceptual Uncertainty Aware Responsibility Sensitive Safety with ML.
Benchmarking Uncertainty Estimation Methods for Deep Learning With Safety-Related Metrics.
A High Probability Safety Guarantee for Shifted Neural Network Surrogates.
You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods.
A Study on Multimodal and Interactive Explanations for Visual Question Answering.
Fair Enough: Improving Fairness in Budget-Constrained Decision Making Using Confidence Thresholds.
Michiel A. Bakker Humberto Riverón Valdés Duy Patrick Tu Krishna P. Gummadi Kush R. Varshney Adrian Weller Alex Pentland
Exploring AI Safety in Degrees: Generality, Capability and Control.
Founding The Domain of AI Forensics.
Assurance Argument Patterns and Processes for Machine Learning in Safety-Related Systems.
Hazard Contribution Modes of Machine Learning Components.
Adversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems.
Bio-Inspired Adversarial Attack Against Deep Neural Networks.