MetaV
Authors:
Open Access
- 14 August 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1327-1336
Abstract
Protecting the intellectual property (IP) of deep neural networks (DNN) becomes an urgent concern for IT corporations. For model piracy forensics, previous model fingerprinting schemes are commonly based on adversarial examples constructed for the owner's model as the fingerprint, and verify whether a suspect model is indeed pirated from the original model by matching the behavioral pattern on the fingerprint examples between one another. However, these methods heavily rely on the characteristics of classification tasks which inhibits their application to more general scenarios. To address this issue, we present MetaV, the first task-agnostic model fingerprinting framework which enables fingerprinting on a much wider range of DNNs independent from the downstream learning task, and exhibits strong robustness against a variety of ownership obfuscation techniques. Specifically, we generalize previous schemes into two critical design components in MetaV: the adaptive fingerprint and the meta-verifier, which are jointly optimized such that the meta-verifier learns to determine whether a suspect model is stolen based on the concatenated outputs of the suspect model on the adaptive fingerprint. As a key of being task-agnostic, the full process makes no assumption on the model internals in the ensemble only if they have the same input and output dimensions. Spanning classification, regression and generative modeling, extensive experimental results validate the substantially improved performance of MetaV over the state-of-the-art fingerprinting schemes and demonstrate the enhanced generality of MetaV for providing task-agnostic fingerprinting. For example, on fingerprinting ResNet-18 trained for skin cancer diagnosis, MetaV achieves simultaneously 100% true positives and 100% true negatives on a diverse test set of 70 suspect models, achieving an about 220% relative improvement in ARUC over the optimal baseline.Keywords
This publication has 9 references indexed in Scilit:
- Protecting artificial intelligence IPs: a survey of watermarking and fingerprinting for machine learningCAAI Transactions on Intelligence Technology, 2021
- Neural Network Stealing via Meltdown2021
- Regularized Evolution for Image Classifier Architecture SearchProceedings of the AAAI Conference on Artificial Intelligence, 2019
- BAM! Born-Again Multi-Task Networks for Natural Language Understanding2019
- Protecting Intellectual Property of Deep Neural Networks with Watermarking2018
- Embedding Watermarks into Deep Neural Networks2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Pharmacogenomics Knowledge for Personalized MedicineClinical Pharmacology & Therapeutics, 2012