AISafety 2019
Artificial Intelligence Safety 2019

Table of Contents

• Preface
  

Frontmatter

• Author Index
  
• Keyword Index
  
• Table of Contents

Invited Talk

• Towards a Framework for Safety Assurance of Autonomous Systems
  John McDermid, Yan Jia, Ibrahim Habli

Session 1: Safe Learning

• Learning Modular Safe Policies in the Bandit Setting with Application to Adaptive Clinical Trials
  Hossein Aboutalebi, Doina Precup, Tibor Schuster
• Metric Learning for Value Alignment
  Andrea Loreggia, Nicholas Mattei, Francesca Rossi, Kristen Brent Venable

Session 2: Reinforcement Learning Safety

• Penalizing Side Effects using Stepwise Relative Reachability
  Victoria Krakovna, Laurent Orseau, Miljan Martic, Shane Legg
• Conservative Agency
  Alexander Turner, Dylan Hadfield-Menell, Prasad Tadepalli
• Detecting Spiky Corruption in Markov Decision Processes
  Jason Mancuso, Tomasz Kisielewski, David Lindner, Alok Singh
• Modeling AGI Safety Frameworks with Causal Influence Diagrams
  Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg

Session 3: Safe Autonomous Vehicles

• On the Susceptibility of Deep Neural Networks to Natural Perturbations
  Mesut Ozdag, Sunny Raj, Steven L. Fernandes, Alvaro Velasquez, Laura Pullum, Sumit Kumar Jha
• Managing Uncertainty of AI-based Perception for Autonomous Systems
  Maximilian Henne, Adrian Schwaiger, Gereon Weiss
• A Framework for Safety Violation Identification and Assessment in Autonomous Driving
  Lukas Heinzmann, Sina Shafaei, Mohd Hafeez Osman, Christoph Segler, Alois Knoll

Session 4: AI Value Alignment, Ethics and Bias

• The Glass Box Approach: Verifying Contextual Adherence to Values
  Andrea Aler Tubella, Virginia Dignum
• Requisite Variety in Ethical Utility Functions for AI Value Alignment
  Nadisha-Marie Aliman, Leon Kester
• Slam the Brakes: Perceptions of Moral Decisions in Driving Dilemmas
  Holly Wilson, Andreas Theodorou
• Understanding Bias in Datasets using Topological Data Analysis
  Ramya Srinivasan, Ajay Chander

Poster Papers

• Computational Strategies for the Trustworthy Pursuit and the Safe Modeling of Probabilistic Maintenance Commitments
  Qi Zhang, Edmund Durfee, Satinder Singh
• Categorizing Wireheading in Partially Embedded Agents
  Arushi Majha, Sayan Sarkar, Davide Zagami
• Adversarial Exploitation of Policy Imitation
  Vahid Behzadan, William Hsu
• The Challenge of Imputation in Explainable Artificial Intelligence Models
  Muhammad Ahmad, Carly Eckert, Ankur Teredesai
• On the Importance of System Testing for Assuring Safety of AI Systems
  Franz Wotawa
• Towards Empathic Deep Q-Learning
  Bart Bussmann, Jacqueline Heinerman, Joel Lehman
• Watermarking of DRL Policies with Sequential Triggers
  Vahid Behzadan, William Hsu