Who is Responsible for Adversarial Defense?
It addresses the problem of accountability in adversarial defense for AI researchers and practitioners, but is incremental as it frames an existing issue rather than proposing new solutions.
This paper discusses the responsibility for implementing and validating adversarial defenses in AI/ML systems, focusing on identifying vulnerable components and necessary expertise, without presenting specific results or numbers.
We have seen a surge in research aims toward adversarial attacks and defenses in AI/ML systems. While it is crucial to formulate new attack methods and devise novel defense strategies for robustness, it is also imperative to recognize who is responsible for implementing, validating, and justifying the necessity of these defenses. In particular, which components of the system are vulnerable to what type of adversarial attacks, and the expertise needed to realize the severity of adversarial attacks. Also how to evaluate and address the adversarial challenges in order to recommend defense strategies for different applications. This paper opened a discussion on who should examine and implement the adversarial defenses and the reason behind such efforts.