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

arXiv: https://arxiv.org/abs/2203.09681 · HTML: https://mlsanity.com/paper/2203.09681/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2022.

## Built on by (most cited first, 1 of 1)

- [CiliaGraph: Enabling Expression-enhanced Hyper-Dimensional Computation in Ultra-Lightweight and One-Shot Graph Classification on Edge](https://mlsanity.com/paper/2405.19033/) (2024)

## Abstract (arXiv)

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.