Privacy and Integrity Preserving Training Using Trusted Hardware

Authors: Hanieh Hashemi, Yongqin Wang, Murali Annavaram
Published: 2021-05-01

Source: https://arxiv.org/abs/2105.00334

PDF: https://arxiv.org/pdf/2105.00334

AIにより推定されたラベル

プライバシー保護 データプライバシー評価 データ整合性制約

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However, Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. This work presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides privacy and integrity verification, while accelerators perform the computation heavy linear algebraic operations.