Software PUFs surveyed for hardware roots of trust in edge AI
Original title: Toward Deployable Hardware Roots of Trust for Edge AI: Software PUFs and Their Trade-offs
Survey of 37 software PUF works highlights trade-offs for boot-time key derivation and response latency in edge AI.
The paper surveys software PUFs as alternatives to hardware modifications for securing edge AI devices. It compares approaches based on entropy sources and software methods. Four key challenges are outlined for real-world adoption in long-lifespan devices.
- Software PUFs derive unique responses without post-fabrication changes
- Boot-time versus runtime key derivation analyzed
- Response latency compared across approaches
- Fragmented research lacks holistic trade-off review
From the original article
1 min read at arxiv.orgDeploying AI at the edge increases the need for security features on existing devices. When physical access to the device is available, storing secret keys in non-volatile memory is vulnerable.
By Yilin Li · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.