TPUXtract: An Exhaustive Hyperparameter Extraction Framework

Abstract: Model stealing attacks on AI/ML devices undermine intellectual property rights, compromise the competitive advantage of the original model developers, and potentially expose sensitive data embedded in the model’s behavior to unauthorized parties. While previous research works have demonstrated successful side-channelbased model recovery in embedded microcontrollers and FPGA-based accelerators, the exploration of attacks on commercial ML accelerators remains largely unexplored. Moreover, prior side-channel attacks fail when they encounter previously unknown models. This paper demonstrates the first successful model extraction attack on the Google Edge Tensor Processing Unit (TPU), an off-the-shelf ML accelerator. Specifically, we show a hyperparameter stealing attack that can extract all layer configurations including the layer type, number of nodes, kernel/filter sizes, number of filters, strides, padding, and activation function. Most notably, our attack is the first comprehensive.... https://ojs.ub.rub.de/index.php/TCHES/article/view/11923

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch

References and Relationships

• Bibliographic citation: TPUXtract: An Exhaustive Hyperparameter Extraction Framework ; volume:2025 ; number:1 ; year:2024 ; IACR transactions on cryptographic hardware and embedded systems ; 2025, Heft 1 (2024)

Contributors, Places and Time

• Creator: Kurian, Ashley ; Dubey, Anuj ; Yaman, Ferhat ; Aysu, Aydin

Further information

• DOI: 10.46586/tches.v2025.i1.78-103
• URN: urn:nbn:de:101:1-2412181754102.790692711547
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 15.08.2025, 7:28 AM CEST