SafeAI 2020
Artificial Intelligence Safety 2020

Table of Contents

• Preface
  
  
• Contents
  
  
• Keyword Index
  
  
• Author Index
  
  

Session 1: Adversarial Machine Learning

• Bio-Inspired Adversarial Attack Against Deep Neural Networks 1-5
  Bowei Xi, Yujie Chen, Fei Fan, Zhan Tu, Xinyan Deng
• Adversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems 6-13
  Kazuya Kakizaki, Kosuke Yoshida

Session 2: Assurance Cases for AI-based Systems

• Hazard Contribution Modes of Machine Learning Components 14-22
  Ewen Denney, Ganesh Pai, Colin Smith
• Assurance Argument Patterns and Processes for Machine Learning in Safety-Related Systems 23-30
  Chiara Picardi, Colin Paterson, Richard Hawkins, Radu Calinescu, Ibrahim Habli

Session 3: Considerations for the AI Safety Landscape

• Founding The Domain of AI Forensics 31-35
  Vahid Behzadan, Ibrahim Baggili
• Exploring AI Safety in Degrees: Generality, Capability and Control 36-40
  John Burden, José Hernández-Orallo

Session 4: Fairness and Bias

• Fair Enough: Improving Fairness in Budget-Constrained Decision Making Using Confidence Thresholds 41-53
  Michiel Bakker, Humberto Riveron Valdes, Duy Patrick Tu, Krishna Gummadi, Kush Varshney, Adrian Weller, Alex Pentland
• A Study on Multimodal and Interactive Explanations for Visual Question Answering 54-62
  Kamran Alipour, Jurgen P. Schulze, Yi Yao, Avi Ziskind, Giedrius Burachas
• You Shouldn’t Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods 63-73
  Botty Dimanov, Umang Bhatt, Mateja Jamnik, Adrian Weller

Session 5: Uncertainty and Safe AI

• A High Probability Safety Guarantee for Shifted Neural Network Surrogates 74-82
  Melanie Ducoffe, Sebastien Gerchinovitz, Jayant Sen Gupta
• Benchmarking Uncertainty Estimation Methods for Deep Learning With Safety-Related Metrics 83-90
  Maximilian Henne, Adrian Schwaiger, Karsten Roscher, Gereon Weiss
• PURSS: Towards Perceptual Uncertainty Aware Responsibility Sensitive Safety with ML 91-95
  Rick Salay, Krzysztof Czarnecki, Maria Elli, Ignacio Alvarez, Sean Sedwards, Jack Weast

Poster Papers

• Simple Continual Learning Strategies for Safer Classifers 96-104
  Ashish Gaurav, Sachin Vernekar, Jaeyoung LeeSean Sedwards, Vahdat Abdelzad, Krzysztof Czarnecki, Sean Sedwards
• Fair Representation for Safe Artificial Intelligence via Adversarial Learning of Unbiased Information Bottleneck 105-112
  Jin-Young Kim, Sung-Bae Cho
• Out-of-Distribution Detection with Likelihoods Assigned by Deep Generative Models Using Multimodal Prior Distributions 113-116
  Ryo Kamoi, Kei Kobayashi
• SafeLife 1.0: Exploring Side Effects in Complex Environments 117-127
  Carroll Wainwright, Peter Eckersley
• (When) Is Truth-telling Favored in AI Debate? 128-137
  Vojtech Kovarik, Ryan Carey
• NewsBag: A Benchmark Multimodal Dataset for Fake News Detection 138-145
  Sarthak Jindal, Raghav Sood, Richa Singh, Mayank Vatsa, Tanmoy Chakraborty
• Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometrics 146-152
  Ignacio Serna, Aythami Morales, Julian Fierrez, Manuel Cebrian, Nick Obradovich, Iyad Rahwan
• Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints 153-161
  Bharat Prakash, Nicholas Waytowich, Ashwinkumar Ganesan, Tim Oates, Tinoosh Mohsenin
• Practical Solutions for Machine Learning Safety in Autonomous Vehicles 162-169
  Sina Mohseni, Mandar Pitale, Vasu Singh, Zhangyang Wang
• Continuous Safe Learning Based on First Principles and Constraints for Autonomous Driving 170-177
  Lifeng Liu, Yingxuan Zhu, Tim Yuan, Jian Li
• Recurrent Neural Network Properties and their Verification with Monte Carlo Techniques 178-185
  Dmitry Vengertsev, Elena Sherman
• Toward Operational Safety Verification Via Hybrid Automata Mining Using I/O Traces of AI-Enabled CPS 186-194
  Imane Lamrani, Ayan Banerjee, Sandeep Gupta