AISafety 2022
Artificial Intelligence Safety 2022

Table of Contents

• Preface
  
  

Session 1: AI Ethics: Fairness, Bias, and Accountability

• Let it RAIN for Social Good
  Mattias Brännström, Andreas Theodorou, Virginia Dignum
• Accountability and Responsibility of Artificial Intelligence Decision-making Models in Indian Policy Landscape
  Palak Malhotra, Amita Misra
• Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognition
  Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

Session 2: Short Presentations - Safety Assessment of AI-enabled systems

• A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems
  Yi Qi, Philippa Ryan Conmy, Wei Huang, Xingyu Zhao, Xiaowei Huang
• Increasingly Autonomous CPS: Taming Emerging Behaviors from an Architectural Perspective
  Jerome Hugues, Daniela Cancila
• CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness
  Julien Girard-Satabin, Michele Alberti, François Bobot, Zakaria Chihani, Augustin Lemesle

Session 3: Machine Learning for Safety-critical AI

• Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection
  Patrick Feifel, Benedikt Franke, Arne Raulf, Friedhelm Schwenker, Frank Bonarens, Frank Köster
• Improvement of Rejection for AI Safety through Loss-Based Monitoring
  Daniel Scholz, Florian Hauer, Klaus Knobloch, Christian Mayr

Session 4: Short Presentations - ML Robustness, Criticality and Uncertainty

• Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers
  Georg Siedel, Silvia Vock, Andrey Morozov, Stefan Voß
• Safety-aware Active Learning with Perceptual Ambiguity and Criticality Assessment
  Prajit T Rajendran, Guillaume Ollier, Huascar Espinoza, Morayo Adedjouma, Agnes Delaborde, Chokri Mraidha
• Understanding Adversarial Examples Through Deep Neural Network's Classification Boundary and Uncertainty Regions
  Juan Shu, Bowei Xi, Charles Kamhoua

Session 5: AI Robustness, Generative Models and Adversarial Learning

• Leveraging generative models to characterize the failure conditions of image classifiers
  Adrien Le Coz, Stéphane Herbin, Faouzi Adjed
• Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection
  Svetlana Pavlitskaya, Bianca-Marina Codău, J. Marius Zöllner
• Privacy Safe Representation Learning via Frequency Filtering Encoder
  Jonghu Jeong, Minyong Cho, Philipp Benz, Jinwoo Hwang, Jeewook Kim, Seungkwan Lee, Tae-hoon Kim
• Benchmarking and deeper analysis of adversarial patch attack on object detectors
  Pol Labarbarie, Adrien Chan Hon Tong, Stéphane Herbin, Milad Leyli-Abadi

Session 6: AI Accuracy, Diversity, Causality and Optimization

• The impact of averaging logits over probabilities on ensembles of neural networks
  Cedrique Rovile Njieutcheu Tassi, Jakob Gawlikowski, Auliya Unnisa Fitri, Rudolph Triebel
• Exploring Diversity in Neural Architectures for Safety
  Michał Filipiuk, Vasu Singh
• Constrained Policy Optimization for Controlled Contextual Bandit Exploration
  Mohammad Kachuee, Sungjin Lee
• A causal perspective on AI deception in games
  Francis Rhys Ward, Francesco Belardinelli, Francesca Toni