Print Email Facebook Twitter Deterministic and Statistical Strategies to Protect ANNs against Fault Injection Attacks Title Deterministic and Statistical Strategies to Protect ANNs against Fault Injection Attacks Author Köylü, T.C. (TU Delft Computer Engineering) Reinbrecht, Cezar (TU Delft Computer Engineering) Hamdioui, S. (TU Delft Quantum & Computer Engineering) Taouil, M. (TU Delft Computer Engineering) Department Quantum & Computer Engineering Date 2021 Abstract Artificial neural networks are currently used for many tasks, including safety critical ones such as automated driving. Hence, it is very important to protect them against faults and fault attacks. In this work, we propose two fault injection attack detection mechanisms: one based on using output labels for a reference input, and the other on the activations of neurons. First, we calibrate our detectors during normal conditions. Thereafter, we verify them to maximize fault detection performance. To prove the effectiveness of our solution, we consider highly employed neural networks (AlexNet, GoogleNet, and VGG) with their associated dataset ImageNet. Our results show that for both detectors we are able to obtain a high rate of coverage against faults, typically above 96%. Moreover, the hardware and software implementations of our detector indicate an extremely low area and time overhead. Subject Fault InjectionCountermeasuresArtificial neural networksMachine learning To reference this document use: http://resolver.tudelft.nl/uuid:341ae459-f1a4-4346-aff9-45c7ed14c446 DOI https://doi.org/10.1109/PST52912.2021.9647763 Publisher IEEE, Piscataway ISBN 978-1-6654-0185-2 Source 2021 18th International Conference on Privacy, Security and Trust (PST) Event 18th Annual International Conference on Privacy, Security and Trust (PST2021), 2021-12-13 → 2021-12-15, Virtual at Auckland, New Zealand Series 2021 18th International Conference on Privacy, Security and Trust, PST 2021 Part of collection Institutional Repository Document type conference paper Rights © 2021 T.C. Köylü, Cezar Reinbrecht, S. Hamdioui, M. Taouil Files PDF no_threadmark.pdf 638.09 KB Close viewer /islandora/object/uuid:341ae459-f1a4-4346-aff9-45c7ed14c446/datastream/OBJ/view