Founding The Domain of AI Forensics
This work addresses the need for legally and scientifically sound investigations into AI failures, which is crucial for safety and accountability as AI becomes more integrated into critical technologies.
The paper tackles the problem of investigating AI system failures by proposing the establishment of AI Forensics as a new discipline under AI safety, inspired by cyber forensics, and outlines a taxonomy and foundational challenges for this area.
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.