SafeAI 2019

SafeAI is the AAAI's Workshop on Artificial Intelligence Safety.

It was held in January 27, 2019, in Honolulu, Hawaii (USA) as part of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) - one of the world's leading AI conferencea.  SafeAI aims to explore new ideas on AI safety engineering, ethically aligned design, regulation and standards for AI-based systems. These regular workshops embed safety in the wider field, and provide a publication venue for high-quality AI safety research. 22 papers were presented, and can be read in full here.

The Best Paper Award was won by a team from IBM Research: Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering - Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian Molloy, Biplav Srivastava

bestpaper

The other best paper candidates were: 

The Workshop also featured Keynotes:

  • Dr. Sandeep Neema (DARPA), Assured Autonomy
  • Prof. Francesca Rossi (IBM and University of Padova), Ethically Bounded AI

and Invited Talks:

  • Dr. Ian Goodfellow (Google Brain), Adversarial Robustness for AI Safety
  • Prof. Alessio R. Lomuscio (Imperial College London), Reachability Analysis for Neural Agent-Environment Systems

Read full proceedings

Session 1: Safe Planning and Operation of Autonomous Systems

  • Minimizing the Negative Side Effects of Planning with Reduced Models
    Sandhya Saisubramanian, Shlomo Zilberstein
  • Robust Motion Planning and Safety Benchmarking in Human Workspaces
    Shih-Yun Lo, Shani Alkoby, Peter Stone
  • Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization
    Mark Riedl, Brent Harrison

Session 2: New Paradigms in AI and AGI Safety

  • Towards Robust End-to-End Alignment
    Lê Nguyên Hoang
  • Integrative Biological Simulation, Neuropsychology, and AI Safety
    Gopal Sarma, Adam Safron, Nick Hay

Session 3: Safety in Automated Driving

  • How Many Operational Design Domains, Objects, and Events?
    Philip Koopman, Frank Fratrik
  • Monitoring Safety of Autonomous Vehicles with Crash Prediction Networks
    Saasha Nair, Sina Shafaei, Stefan Kugele, Mohd Hafeez Osman, Alois Knoll

Session 4: Safety-Related AI Requirements and Characteristics

  • Requirements Assurance in Machine Learning
    Alec Banks, Rob Ashmore
  • Surveying Safety-relevant AI Characteristics
    Jose Hernandez-Orallo, Fernando Martínez-Plumed, Shahar Avin, Sean O Heigeartaigh

Session 5: Adversarial Machine Learning

  • Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
    Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian Molloy, Biplav Srivastava
  • DPATCH: An Adversarial Patch Attack on Object Detectors
    Xin Liu, Huanrui Yang, Ziwei Liu, Linghao Song, Yiran Chen, Hai Li
  • Attacks on Machine Learning: Lurking Danger for Accountability
    Katja Auernhammer, Ramin Tavakoli Kolagari, Markus Zoppelt

Short Poster Papers

  • Towards International Standards for Evaluating Machine Learning
    Frank Rudzicz, P Alison Paprica, Marta Janczarski
  • Counterfactual Explanations of Machine Learning Predictions: Opportunities and Challenges for AI Safety
    Kacper Sokol, Peter Flach
  • Safe Temporal Planning for Urban Driving
    Bence Cserna, William Doyle, Tianyi Gu, Wheeler Ruml
  • Linking Artificial Intelligence Principles
    Yi Zeng, Enmeng Lu, Cunqing Huangfu
  • Emergence of Addictive Behaviors in Reinforcement Learning Agents
    Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir
  • Temporally Extended Metrics for Markov Decision Processes
    Philip Amortila, Marc G. Bellemare, Prakash Panangaden, Doina Precup
  • AutoMPC: Efficient Multi-Party Computation for Secure and Privacy-Preserving Cooperative Control of Connected Autonomous Vehicles
    Tao Li, Lei Lin, Siyuan Gong
  • Security-preserving Support Vector Machine with Fully Homomorphic Encryption
    Saerom Park, Jaewook Lee, Jung Hee Cheon, Juhee Lee, Jaeyun Kim, Junyoung Byun
  • Bamboo: Ball-Shape Data Augmentation Against Adversarial Attacks from All Directions
    Huanrui Yang, Jingchi Zhang, Hsin-Pai Cheng, Wenhan Wang, Yiran Chen, Hai Li
poster session

Subscribe to our mailing list to get our latest updates