The AAAI organizing committee has decided that all sessions will be held as a Virtual event.

Feb 8, 2021. Schedule from 8:00 to 16:30 UTC [0:00-8:30 PST]

Time (UTC)

Description  (Presentation files available in Links below)

8:00-8:05 Welcome and Introduction

Keynote: Christophe Gabreau (Airbus, co-chair of EUROCAE WG-114 Group), Beatrice Pesquet-Popescu (Thales, co-chair of EUROCAE WG-114 Group), Fateh Kaakai (Thales, Sub-Group Leader of EUROCAE WG-114 Group), EUROCAE WG114 – SAE G34: a joint standardization initiative to support Artificial Intelligence revolution in aeronautics.

Session 1: Dynamic Safety and Anomaly Assessment – Chair: Huascar Espinoza

Feature Space Singularity for Out-of-Distribution Detection, Haiwen Huang, Zhihan Li, Lulu Wang, Sishuo Chen, Xinyu Zhou and Bin Dong.
An Evaluation of “Crash Prediction Networks” (CPN) for Autonomous Driving Scenarios in CARLA Simulator, Saasha Nair, Sina Shafaei, Daniel Auge and Alois Knoll.
From Black-box to White-box: Examining Confidence Calibration under different Conditions, Franziska Schwaiger, Maximilian Henne, Fabian Küppers, Felippe Schmoeller Roza, Karsten Roscher and Anselm Haselhoff.
– Debate Panel – Paper Discussants: Xin Cynthia Chen, Rob Ashmore.

Poster Pitches 1 – (2 mins x pitch)

– Towards an Ontological Framework for Environmental Survey Hazard Analysis of Autonomous Systems, Christopher Harper and Praminda Caleb-Solly.
– Overestimation learning with guarantees, Adrien Gauffriau, François Malgouyres and Mélanie Ducoffe.
On the Use of Available Testing Methods for Verification & Validation of AI-based Software and Systems, Franz Wotawa.
– Runtime Decision Making Under Uncertainty in Autonomous Vehicles, Vibhu Gautam, Youcef Gheraibia, Rob Alexander and Richard Hawkins.

10:00-10:30 Poster Exhibition & Virtual Coffee Break
10:30-10:50 Invited Talk: Juliette Mattioli (Thales, France) and Rodolphe Gelin (Renault, France). Methods and tools for trusted AI: an urgent challenge for industry.
Session 2: Safety Considerations for the Assurance of AI-based Systems – Chair: Xin Cynthia Chen

The Utility of Neural Network Test Coverage Measures, Rob Ashmore and Alec Banks.
Safety Properties of Inductive Logic Programming, Gavin Leech, Nandi Schoots and Joar Skalse.
A Hybrid-AI Approach for Competence Assessment of Automated Driving functions, Jan-Pieter Paardekooper, Mauro Comi, Corrado Grappiolo, Ron Snijders, Willeke van Vught and Rutger Beekelaar.
– Debate Panel – Paper Discussants: Xiaowei Huang, Huascar Espinoza.

Poster Pitches 2 – (2 mins x pitch)

Negative Side Effects and AI Agent Indicators: Experiments in SafeLife, John Burden, Jose Hernandez-Orallo and Sean O’Heigeartaigh.
Time for AI (Ethics) Maturity Model Is Now, Ville Vakkuri, Marianna Jantunen, Erika Halme, Kai-Kristian Kemell, Anh Nguyen-Duc, Tommi Mikkonen and Pekka Abrahamsson.
– AI-Blueprint for Deep Neural Networks, Ernest Wozniak, Henrik Putzer and Carmen Carlan.
Neural Criticality: Validation of Convolutional Neural Networks, Vaclav Divis and Marek Hruz.

12:00-13:00 Poster Exhibition & Virtual Lunch
13:00-13:20 Invited Talk: Sandhya Saisubramanian (University of Massachusetts Amherst, USA), Challenges and Directions in Avoiding Negative Side Effects.
Session 3: Adversarial Machine Learning and Trustworthiness – Chair: Richard Mallah

Adversarial Robustness for Face Recognition: How to Introduce Ensemble Diversity among Feature Extractors?, Takuma Amada, Kazuya Kakizaki, Seng Pei Liew, Toshinori Araki, Joseph Keshet and Jun Furukawa.
Multi-Modal Generative Adversarial Networks Make Realistic and Diverse but Untrustworthy Predictions When Applied to Ill-posed Problems, John Hyatt and Michael Lee.
DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation, Javier Hernandez-Ortega, Ruben Tolosana, Julian Fierrez and Aythami Morales.
– Debate Panel – Paper Discussants: José Hernández-Orallo, Ville Vakkuri.

Poster Pitches 3 – (2 mins x pitch)

Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data, Francesco Cartella, Orlando Anunciacao, Yuki Funabiki, Daisuke Yamaguchi, Toru Akishita and Olivier Elshocht.
Correct-by-Construction Multi-Label Classification Networks. Eleonora Giunchiglia and Thomas Lukasiewicz.
– Classification confidence scores with point-wise guarantees, Nivasini Ananthakrishnan, Shai Ben-David and Tosca Lechner.

14:30-15:00 Poster Exhibition & Virtual Coffee Break
Session 4: Safe Autonomous Agents – Chair: José Hernández-Orallo

What criminal and civil law tells us about Safe RL techniques to generate law-abiding behaviour, Hal Ashton.
Performance of Bounded-Rational Agents With the Ability to Self-Modify. Jakub Tětek, Marek Sklenka and Tomáš Gavenčiak.
Deep CPT-RL: Imparting Human-Like Risk Sensitivity to Artificial Agents, Jared Markowitz, Marie Chau and I-Jeng Wang.
Challenges for Using Impact Regularizers to Avoid Negative Side Effects, David Lindner, Kyle Matoba and Alexander Meulemans.
– Debate Panel – Paper Discussants: Sean O’Heigeartaigh, Richard Mallah.

16:20-16:30 Wrap-up and Best Paper Award