AISafety 2020
Artificial Intelligence Safety 2020

Table of Contents

• Preface
  
  

Session 1: Adversarial Machine Learning

• Understanding the One Pixel Attack: Propagation Maps and Locality Analysis
  Danilo Vasconcellos Vargas, Jiawei Su
• Error-Silenced Quantization: Bridging Robustness and Compactness
  Zhicong Tang, Yinpeng Dong, Hang Su
• Evolving Robust Neural Architectures to Defend from Adversarial Attacks
  Shashank Kotyan, Danilo Vasconcellos Vargas

Session 2: AI Safety Landscape

• Safety of Artificial Intelligence: A Collaborative Model
  John McDermid, Yan Jia

Session 3: Safe and Value-Aligned Learning in Decision Making

• Choice Set Misspecification in Reward Inference
  Rachel Freedman, Rohin Shah, Anca Dragan
• Safety Augmentation in Decision Trees
  Sumanta Dey, Pallab Dasgupta, Briti Gangopadhyay
• Aligning with Heterogenous Preferences for Kidney Exchange
  Rachel Freedman

Session 4: DNN Testing and Runtime Monitoring

• Is Uncertainty Quantification in Deep Learning Sufficient for Out-of-Distribution Detection?
  Adrian Schwaiger, Poulami Sinhamahapatra, Jens Gansloser, Karsten Roscher
• DeepSmartFuzzer: Reward Guided Test Generation For Deep Learning
  Samet Demir, Hasan Ferit Eniser, Alper Sen
• A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications
  Fabio Arnez, Huascar Espinoza, Ansgar Radermacher, François Terrier
• Increasing the Trustworthiness of Deep Neural Networks via Accuracy Monitoring
  Zhihui Shao, Jianyi Yang, Shaolei Ren

Poster Papers

• Robustness as Inherent Property of Datapoints (short paper)
  Catalin-Andrei Ilie, Marius Popescu, Alin Stefanescu
• Towards Safe and Reliable Robot Task Planning (short paper)
  Snehasis Banerje
• Extracting Money from Causal Decision Theorists
  Caspar Oesterheld, Vincent Conitzer
• Ethically Compliant Planning in Moral Autonomous Systems
  Justin Svegliato, Samer Nashed, Shlomo Zilberstein
• Bayesian Model for Trustworthiness Analysis of Deep Learning Classifiers
  Andrey Morozov, Emil Valiev, Michael Beyer, Kai Ding, Lydia Gauerhof, Christoph Schorn