Towards AI Forensics: Did the Artificial Intelligence System Do It?

TL;DR

This paper explores forensic methods to determine if and how an AI system caused a specific event, focusing on malicious AI and grey box analysis, highlighting challenges and potential strategies.

Contribution

It provides a conceptual framework for AI forensic investigation, emphasizing malicious AI detection and grey box analysis, supported by CNN-based evaluation.

Findings

Identifies challenges in AI forensic analysis

Proposes strategies for malicious AI detection

Uses CNNs to illustrate forensic challenges

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 grey box analysis. Our evaluation using convolutional neural networks illustrates challenges and ideas for identifying malicious AI.