When Your AI Becomes a Target: AI Security Incidents and Best Practices
Kathrin Grosse, Lukas Bieringer, Tarek R. Besold, Battista Biggio, Alexandre Alahi
Abstract
In contrast to vast academic efforts to study AI security, few real-world reports of AI security incidents exist. Released incidents prevent a thorough investigation of the attackers' motives, as crucial information about the company and AI application is missing. As a consequence, it often remains unknown how to avoid incidents. We tackle this gap and combine previous reports with freshly collected incidents to a small database of 32 AI security incidents. We analyze the attackers' target and goal, influencing factors, causes, and mitigations. Many incidents stem from non-compliance with best practices in security and privacy-enhancing technologies. In the case of direct AI attacks, access control may provide some mitigation, but there is little scientific work on best practices. Our paper is thus a call for action to address these gaps.
BibTeX
@article{Grosse_Bieringer_Besold_Biggio_Alahi_2024, title={When Your AI Becomes a Target: AI Security Incidents and Best Practices}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30347}, DOI={10.1609/aaai.v38i21.30347}, abstractNote={In contrast to vast academic efforts to study AI security, few real-world reports of AI security incidents exist. Released incidents prevent a thorough investigation of the attackers’ motives, as crucial information about the company and AI application is missing. As a consequence, it often remains unknown how to avoid incidents. We tackle this gap and combine previous reports with freshly collected incidents to a small database of 32 AI security incidents. We analyze the attackers’ target and goal, influencing factors, causes, and mitigations. Many incidents stem from non-compliance with best practices in security and privacy-enhancing technologies. In the case of direct AI attacks, access control may provide some mitigation, but there is little scientific work on best practices. Our paper is thus a call for action to address these gaps.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Grosse, Kathrin and Bieringer, Lukas and Besold, Tarek R. and Biggio, Battista and Alahi, Alexandre}, year={2024}, month={Mar.}, pages={23041-23046} }