The article “Towards AI forensics: Did the artificial intelligence system do it?” has been accepted by the Journal of Information Security and Application (JISA, Elsevier) for open access publication. Details about the article are listed below. Special thanks to my former colleague and co-author Johannes Schneider.
Note, that a first draft of this paper has been released earlier and is available via arxiv.org.
Abstract
Artificial intelligence (AI) makes decisions impacting our daily lives in an increasingly autonomous manner. Their actions might cause accidents, harm, or, more generally, violate regulations. Determining whether an AI caused a specific event and, if so, what triggered the AI's action, are key forensic questions. We provide a conceptualization of the problems and strategies for forensic investigation. We focus on AI that is potentially ``malicious by design'' and gray box analysis. Our evaluation using convolutional neural networks illustrates challenges and ideas for identifying malicious AI.