HDLock: Exploiting Privileged Encoding to Protect Hyperdimensional Computing Models against IP Stealing

• Main Authors: Duan, Shijin, Ren, Shaolei, Xu, Xiaolin
• Format: Journal Article
• Language: English
• Published: 17-03-2022
• Subjects: Computer Science - Cryptography and Security
• DOI: 10.48550/arxiv.2203.09681

Hyperdimensional Computing (HDC) is facing infringement issues due to
straightforward computations. This work, for the first time, raises a critical
vulnerability of HDC, an attacker can reverse engineer the entire model, only
requiring the unindexed hypervector memory. To mitigate this attack, we propose
a defense strategy, namely HDLock, which significantly increases the reasoning
cost of encoding. Specifically, HDLock adds extra feature hypervector
combination and permutation in the encoding module. Compared to the standard
HDC model, a two-layer-key HDLock can increase the adversarial reasoning
complexity by 10 order of magnitudes without inference accuracy loss, with only
21% latency overhead.