Founding The Domain of AI Forensics

Abstract

With the widespread integration of AI in everyday and critical technologies, it seems inevitable to witness increasing instances of failure in AI systems. In such cases, there arises a need for technical investigations that produce legally acceptable and scientifically indisputable findings and conclusions on the causes of such failures. Inspired by the domain of cyber forensics, this paper introduces the need for the establishment of AI Forensics as a new discipline under AI safety. Furthermore, we propose a taxonomy of the subfields under this discipline, and present a discussion on the foundational challenges that lay ahead of this new research area.

arXiv commentAccepted for presentation at SafeAI2020

References in corpus (8)

• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Stealing Machine Learning Models via Prediction APIs
• Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
• Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures
• The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning
• Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies
• Emergence of Addictive Behaviors in Reinforcement Learning Agents