Research Article
On Exploring the Sub-domain of Artificial Intelligence (AI) Model Forensics
@INPROCEEDINGS{10.1007/978-3-031-06365-7_3, author={Tiffanie Edwards and Syria McCullough and Mohamed Nassar and Ibrahim Baggili}, title={On Exploring the Sub-domain of Artificial Intelligence (AI) Model Forensics}, proceedings={Digital Forensics and Cyber Crime. 12th EAI International Conference, ICDF2C 2021, Virtual Event, Singapore, December 6-9, 2021, Proceedings}, proceedings_a={ICDF2C}, year={2022}, month={6}, keywords={Digital forensics Artificial Intelligence AI forensics}, doi={10.1007/978-3-031-06365-7_3} }- Tiffanie Edwards
Syria McCullough
Mohamed Nassar
Ibrahim Baggili
Year: 2022
On Exploring the Sub-domain of Artificial Intelligence (AI) Model Forensics
ICDF2C
Springer
DOI: 10.1007/978-3-031-06365-7_3
Abstract
AI Forensics is a novel research field that aims at providing techniques, mechanisms, processes, and protocols for an AI failure investigation. In this paper, we pave the way towards further exploring a sub-domain of AI forensics, namely AI model forensics, and introduce AI model ballistics as a subfield inspired by forensic ballistics. AI model forensics studies the forensic investigation process, including where available evidence can be collected, as it applies to AI models and systems.
We elaborate on the background and nature of AI model development and deployment, and highlight the fact that these models can be replaced, trojanized, gradually poisoned, or fooled by adversarial input.
The relationships and the dependencies of our newly proposed sub-domain draws from past literature in software, cloud, and network forensics. Additionally, we share a use-case mini-study to explore the peculiarities of AI model forensics in an appropriate context. Blockchain is discussed as a possible solution for maintaining audit trails. Finally, the challenges of AI model forensics are discussed.
