Set-Membership Inference Attacks using Data Watermarking

TL;DR

This paper introduces a set-membership inference attack leveraging deep image watermarking to detect unauthorized use of training data in generative models, demonstrating its effectiveness through empirical results.

Contribution

It presents a novel watermarking-based inference attack method for generative models, enabling detection of non-consensual data usage.

Findings

Watermarking can reveal training data in generative models

The method effectively detects unauthorized data use

Empirical results validate the approach

Abstract

In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques. In particular, we demonstrate how conditional sampling from a generative model can reveal the watermark that was injected into parts of the training data. Our empirical results demonstrate that the proposed watermarking technique is a principled approach for detecting the non-consensual use of image data in training generative models.