Emerging AI security threats for autonomous cars
- Artificial Intelligence has made a significant contribution to autonomous vehicles, from object detection to path planning. However, AI models require a large amount of sensitive training data and are usually computationally intensive to build. The commercial value of such models motivates attackers to mount various attacks. Adversaries can launch model extraction attacks for monetization purposes or steppingstone towards other attacks like model evasion. In specific cases, it even results in destroying brand reputation, differentiation, and value proposition. In addition, IP laws and AIrelated legalities are still evolving and are not uniform across countries. We discuss model extraction attacks in detail with two usecases and a generic killchain that can compromise autonomous cars. It is essential to investigate strategies to manage and mitigate the risk of model theft.
| Author: | Shanthi LekkalaGND, Tanya MotwaniGND, Manojkumar ParmarORCiDGND, Amit PhadkeGND |
|---|---|
| Parent Title (English): | 19\(^{th}\) escar Europe : The World's Leading Automotive Cyber Security Conference (Konferenzveröffentlichung) |
| Subtitle (German): | case studies |
| Document Type: | Part of a Book |
| Language: | English |
| Date of Publication (online): | 2021/09/28 |
| Date of first Publication: | 2021/09/28 |
| Publishing Institution: | Ruhr-Universität Bochum, Universitätsbibliothek |
| Tag: | AIoT Cycle; Adversarial Examples; Artificial Intelligence; Model Extraction; Model Theft; Security |
| First Page: | 5 |
| Last Page: | 10 |
| Dewey Decimal Classification: | Allgemeines, Informatik, Informationswissenschaft / Informatik |
| open_access (DINI-Set): | open_access |
| Konferenz-/Sammelbände: | 19th escar Europe : The World's Leading Automotive Cyber Security Conference |
