CVSep 4, 2023

Safe and Robust Watermark Injection with a Single OoD Image

arXiv:2309.01786v24 citationsh-index: 18
Originality Highly original
AI Analysis

This addresses the challenge of model ownership verification for developers and companies, offering a safer and more efficient alternative to existing methods.

The paper tackles the problem of protecting intellectual property of deep neural networks by proposing a watermark injection technique that uses a single out-of-distribution image as a secret key, achieving robustness against attacks like fine-tuning and pruning without requiring training data.

Training a high-performance deep neural network requires large amounts of data and computational resources. Protecting the intellectual property (IP) and commercial ownership of a deep model is challenging yet increasingly crucial. A major stream of watermarking strategies implants verifiable backdoor triggers by poisoning training samples, but these are often unrealistic due to data privacy and safety concerns and are vulnerable to minor model changes such as fine-tuning. To overcome these challenges, we propose a safe and robust backdoor-based watermark injection technique that leverages the diverse knowledge from a single out-of-distribution (OoD) image, which serves as a secret key for IP verification. The independence of training data makes it agnostic to third-party promises of IP security. We induce robustness via random perturbation of model parameters during watermark injection to defend against common watermark removal attacks, including fine-tuning, pruning, and model extraction. Our experimental results demonstrate that the proposed watermarking approach is not only time- and sample-efficient without training data, but also robust against the watermark removal attacks above.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes