DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware-Reference-Cited by-同舟云学术

DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware

Published:2021-10-17 Issue: Volume: Page:
ISSN:
Container-title:MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture
language:
Short-container-title:

Author:

Hashemi Hanieh¹,Wang Yongqin²,Annavaram Murali²

Affiliation:

1. University of Southern California

2. University of Southern California, United States of America

Funder

Facebook AI Research

Defense Advanced Research Projects Agency (DARPA)

NSF (National Science Foundation)

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3466752.3480112

Reference82 articles.

1. Deep Learning with Differential Privacy

2. Amazon. 2020. Machine Learning on AWS. https://aws.amazon.com/machine-learning Amazon. 2020. Machine Learning on AWS. https://aws.amazon.com/machine-learning

3. Secure large-scale genome-wide association studies using homomorphic encryption

Cited by 26 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Fault-tolerant deep learning inference on CPU-GPU integrated edge devices with TEEs;Future Generation Computer Systems;2024-12

2. Achieving federated logistic regression training towards model confidentiality with semi-honest TEE;Information Sciences;2024-09

3. EdgePro: Edge Deep Learning Model Protection via Neuron Authorization;IEEE Transactions on Dependable and Secure Computing;2024-09

4. A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference;Proceedings of the 19th ACM Asia Conference on Computer and Communications Security;2024-07

5. Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices;IEEE INFOCOM 2024 - IEEE Conference on Computer Communications;2024-05-20