When NAS Meets Watermarking: Ownership Verification of DNN Models via Cache Side Channels

02/06/2021
by   Lou Xiaoxuan, et al.
0

We present a novel watermarking scheme to verify the ownership of DNN models. Existing solutions embedded watermarks into the model parameters, which were proven to be removable and detectable by an adversary to invalidate the protection. In contrast, we propose to implant watermarks into the model 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. We further leverage cache side channels to extract and verify watermarks from the black-box models at inference. Theoretical analysis and extensive evaluations show our scheme has negligible impact on the model performance, and exhibits strong robustness against various model transformations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/31/2019

Modeling Neural Architecture Search Methods for Deep Networks

There are many research works on the designing of architectures for the ...
research
08/17/2022

ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach

Malicious architecture extraction has been emerging as a crucial concern...
research
04/04/2020

A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS

This work proposes a novel Graph-based neural ArchiTecture Encoding Sche...
research
06/07/2019

One-Shot Neural Architecture Search via Compressive Sensing

Neural architecture search (NAS), or automated design of neural network ...
research
07/10/2022

Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics

Network Morphism based Neural Architecture Search (NAS) is one of the mo...
research
10/21/2022

Neural Architectural Backdoors

This paper asks the intriguing question: is it possible to exploit neura...

Please sign up or login with your details

Forgot password? Click here to reset