Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits

Abstract: The adoption of machine learning solutions is rapidly increasing across all parts of society. As the models grow larger, both training and inference of machine learning models is increasingly outsourced, e.g. to cloud service providers. This means that potentially sensitive data is processed on untrusted platforms, which bears inherent data security and privacy risks. In this work, we investigate how to protect distributed machine learning systems, focusing on deep convolutional neural networks. The most common and best-performing mixed MPC approaches are based on HE, secret sharing, and garbled circuits. They commonly suffer from large performance overheads, big accuracy losses, and communication overheads that grow linearly in the depth of the neural network. To improve on these problems, we present Dash, a fast and distributed private convolutional neural network inference scheme secure against malicious attackers. Building on arithmetic garbling gadgets [BMR16] and fancy-garbli.... https://ojs.ub.rub.de/index.php/TCHES/article/view/11935

Angaben zum Objekt

• Standort: Deutsche Nationalbibliothek Frankfurt am Main
• Umfang: Online-Ressource
• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits ; volume:2025 ; number:1 ; year:2024 ; IACR transactions on cryptographic hardware and embedded systems ; 2025, Heft 1 (2024)

Beteiligte, Orts- und Zeitangaben

• Urheber: Sander, Jonas ; Berndt, Sebastian ; Bruhns, Ida ; Eisenbarth, Thomas

Weitere Informationen

• DOI: 10.46586/tches.v2025.i1.420-449
• URN: urn:nbn:de:101:1-2412181758323.797498763925
• Rechteinformation: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Letzte Aktualisierung: 15.08.2025, 07:32 MESZ