Preventing neural network model exfiltration in machine learning hardware accelerators
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 …
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 …
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 …
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 …
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 …
operations. However, the current developments in cloud and edge computing have created …