Security Risks in AI Accelerators: Detecting RTL Vulnerabilities to Model Theft with Formal Verification

Mohamed Shelkamy Ali, Lucas Deutschmann, Johannes Müller 0006, Anna Lena Duque Antón, Mohammad Rahmani Fadiheh, Dominik Stoffel, Wolfgang Kunz. Security Risks in AI Accelerators: Detecting RTL Vulnerabilities to Model Theft with Formal Verification. In IEEE European Test Symposium, ETS 2025, Tallinn, Estonia, May 26-30, 2025. pages 1-6, IEEE, 2025. [doi]

Abstract

Abstract is missing.