Preventing neural network model exfiltration in machine learning hardware accelerators

M Isakov, L Bu, H Cheng… - 2018 Asian Hardware …, 2018 - ieeexplore.ieee.org
Machine learning (ML) models are often trained using private datasets that are very
expensive to collect, or highly sensitive, using large amounts of computing power. The …

A survey on hardware security techniques targeting low-power SoC designs

A Ehret, K Gettings, BR Jordan… - 2019 IEEE High …, 2019 - ieeexplore.ieee.org
In this work, we survey hardware-based security techniques applicable to low-power system-
on-chip designs. Techniques related to a system's processing elements, volatile main …

Iollvm: enhance version of ollvm

C Li, T Huang, X Chen, C Xie, W Wen - arXiv preprint arXiv:2203.03169, 2022 - arxiv.org
Code obfuscation increases the difficulty of understanding programs, improves software
security, and, in particular, OLLVM offers the possibility of cross-platform code obfuscation …

[PDF][PDF] iOLLVM: Enhanced version of OLLVM

CLT Huang, X Chen, C Xie, W Wen - Artificial Intelligence Trends & …, 2022 - csitcp.com
Code obfuscation increases the difficulty of understanding programs, improves software
security, and, in particular, OLLVM offers the possibility of cross-platform code obfuscation …

Eleatic: Secure Architecture across the Edge-to-Cloud Continuum

A Ehret - 2022 - search.proquest.com
Many companies face pressure to deploy flexible compute infrastructures to manage their
operations. However, the current developments in cloud and edge computing have created …