Ownership Verification of DNN Architectures via Hardware Cache Side Channels

TL;DR

This paper introduces a novel method for verifying ownership of DNN architectures by embedding watermarks into the architecture itself using NAS, which is robust against attacks and preserves model performance.

Contribution

The paper proposes a new watermarking scheme that embeds watermarks into DNN architectures via NAS, addressing vulnerabilities of parameter-based watermarks and enhancing IP protection.

Findings

Watermarked models maintain high accuracy.

Watermarks are robust against model transformations.

Scheme exhibits strong resistance to adaptive attacks.

Abstract

Deep Neural Networks (DNN) are gaining higher commercial values in computer vision applications, e.g., image classification, video analytics, etc. This calls for urgent demands of the intellectual property (IP) protection of DNN models. In this paper, we present a novel watermarking scheme to achieve the ownership verification of DNN architectures. Existing works all embedded watermarks into the model parameters while treating the architecture as public property. These solutions were proven to be vulnerable by an adversary to detect or remove the watermarks. In contrast, we claim the model architectures as an important IP for model owners, and propose to implant watermarks into the architectures. We design new algorithms based on Neural Architecture Search (NAS) to generate watermarked architectures, which are unique enough to represent the ownership, while maintaining high model usability. Such watermarks can be extracted via side-channel-based model extraction techniques with high fidelity. We conduct comprehensive experiments on watermarked CNN models for image classification tasks and the experimental results show our scheme has negligible impact on the model performance, and exhibits strong robustness against various model transformations and adaptive attacks.