Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision Models

TL;DR

This paper introduces an adaptive watermarking framework for computer vision models that leverages unique random seed behaviors during training to detect unauthorized model extraction, demonstrating high robustness against various attacks.

Contribution

The paper proposes the RAW framework that uses seed-induced model behaviors as a watermark, providing a novel, robust method for IP protection in model extraction scenarios.

Findings

Achieves >0.9 AUC in detection accuracy.

Robust against unseen extraction attacks and model pruning.

Effective across different model architectures.

Abstract

In recent years, various watermarking methods were suggested to detect computer vision models obtained illegitimately from their owners, however they fail to demonstrate satisfactory robustness against model extraction attacks. In this paper, we present an adaptive framework to watermark a protected model, leveraging the unique behavior present in the model due to a unique random seed initialized during the model training. This watermark is used to detect extracted models, which have the same unique behavior, indicating an unauthorized usage of the protected model's intellectual property (IP). First, we show how an initial seed for random number generation as part of model training produces distinct characteristics in the model's decision boundaries, which are inherited by extracted models and present in their decision boundaries, but aren't present in non-extracted models trained on the same data-set with a different seed. Based on our findings, we suggest the Robust Adaptive Watermarking (RAW) Framework, which utilizes the unique behavior present in the protected and extracted models to generate a watermark key-set and verification model. We show that the framework is robust to (1) unseen model extraction attacks, and (2) extracted models which undergo a blurring method (e.g., weight pruning). We evaluate the framework's robustness against a naive attacker (unaware that the model is watermarked), and an informed attacker (who employs blurring strategies to remove watermarked behavior from an extracted model), and achieve outstanding (i.e., >0.9) AUC values. Finally, we show that the framework is robust to model extraction attacks with different structure and/or architecture than the protected model.