SafeAI 2022
Artificial Intelligence Safety 2022

Table of Contents

• Preface
  
  

Session 1: Bias, Fairness and Value Alignment

• The Problem of Behaviour and Preference Manipulation in AI Systems
  Hal Ashton , Matija Franklin
• IFBiD: Inference-Free Bias Detection
  Ignacio Serna , Daniel DeAlcala , Aythami Morales Moreno , Julian Fierrez , Javier Ortega-Garcia
• Blackbox Post-Processing for Multiclass Fairness
  Preston Putzel , Scott Lee

Session 2: Interpretability and Accountability

• A Gray Box Model for Characterizing Driver Behavior
  Soyeon Jung , Ransalu Senanayake , Mykel Kochenderfer
• Defining and Identifying the Legal Culpability of Side Effects using Causal Graphs
  Hal Ashton

Session 3: Robustness and Uncertainty

• Efficient Adversarial Sequence Generation for RNN with Symbolic Weighted Finite Automata
  Mingjun Ma , Dehui Du , Yuanhao Liu , Yanyun Wang , Yiyang Li
• A Study on Mitigating Hard Boundaries of Decision-Tree-based Uncertainty Estimates for AI Models
  Pascal Gerber , Lisa Jöckel , Michael Kläs
• Quantifying the Importance of Latent Features in Neural Networks
  Amany Alshareef , Nicolas Berthier , Sven Schewe , Xiaowei Huang
• Maximum Likelihood Uncertainty Estimation: Robustness to Outliers
  Deebul Nair , Nico Hochgeschwender , Miguel Olivares-Mendez

Session 4: Safe Reinforcement Learning

• Reinforcement Learning With Imperfect Safety Constraints
  Jin Woo Ro , Gerald Lüttgen , Diedrich Wolter
• Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding
  Chloe He , Borja G. Leon , Francesco Belardinelli
• HiSaRL: A Hierarchical Framework for Safe Reinforcement Learning
  Zikang Xiong , Ishika Agarwal , Suresh Jagannathan
• A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning
  Mathieu Godbout , Maxime Heuillet , Sharath Chandra Raparthy , Rupali Bhati , Audrey Durand

Session 5: AI Testing and Assessment

• Beyond Test Accuracy: The Effects of Model Compression on CNNs
  Adrian Schwaiger , Kristian Schwienbacher , Karsten Roscher
• Using Adaptive Stress Testing to Identify Paths to Ethical Dilemmas in Autonomous Systems
  Ann-Katrin Reuel , Mark Koren , Anthony Corso , Mykel J. Kochenderfer

Poster Papers

• The Dilemma Between Data Transformations and Adversarial Robustness for Time Series Application Systems
  Sheila Alemany , Niki Pissinou
• Interpretable Local Tree Surrogate Policies
  John Mern , Sidhart Krishnan , Anil Yildiz , Kyle Hatch , Mykel J. Kochenderfer
• Oases of Cooperation: An Empirical Evaluation of Reinforcement Learning in the Iterated Prisoner’s Dilemma
  Peter Barnett , John Burden
• Leveraging Multi-task Learning for Unambiguous and Flexible Deep Neural Network Watermarking
  Fangqi Li , Lei Yang , Shilin Wang , Alan Wee-Chung Liew
• Human-in-the-loop Learning for Safe Exploration through Anomaly Prediction and Intervention
  Prajit T Rajendran , Huascar Espinoza , Agnes Delaborde , Chokri Mraidha
• Safety Aware Reinforcement Learning by Identifying Comprehensible Constraints in Expert Demonstrations
  Leopold Müller , Lars Böcking , Michael Färber
• Combining Data-Driven and Knowledge-Based AI Paradigms for Engineering AI-Based Safety-Critical Systems
  Juliette Mattioli , Gabriel Pedroza , Souhaiel Khalfaoui , Bertrand Leroy
• Is it all a cluster game? – Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space
  Poulami Sinhamahapatra , Rajat Koner , Karsten Roscher , Stephan Günnemann
• A Practical Overview of Safety Concerns and Mitigation Methods for Visual Deep Learning Algorithms
  Saeed Bakhshi Germi , Esa Rahtu
• Comparing Vision Transformers and Convolutional Nets for Safety Critical Systems
  Michal Filipiuk , Vasu Singh

Special Sessions

• EnnCore: End-to-End Conceptual Guarding of Neural Architectures
  Edoardo Manino , Danilo Carvalho , Yi Dong , Julia Rozanova , Xidan Song , Mustafa Mustafa , Andre Freitas , Gavin Brown , Mikel Luján , Xiaowei Huang , Lucas Cordeiro
• The wall of safety for AI: approaches in the Confiance.ai program
  Bertrand Braunschweig , Rodolphe Gelin , François Terrier