# Have You Stolen My Model? Evasion Attacks Against Deep Neural Network Watermarking Techniques

arXiv: https://arxiv.org/abs/1809.00615 · HTML: https://mlsanity.com/paper/1809.00615/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations](https://mlsanity.com/paper/2202.08602/) (2022)
- [PassFlow: Guessing Passwords with Generative Flows](https://mlsanity.com/paper/2105.06165/) (2021)
- [When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection](https://mlsanity.com/paper/2308.03573/) (2023)
- [HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks](https://mlsanity.com/paper/2103.13628/) (2021)
- [PCPT and ACPT: Copyright Protection and Traceability Scheme for DNN Models](https://mlsanity.com/paper/2206.02541/) (2022)
- [Non-transferable Pruning](https://mlsanity.com/paper/2410.08015/) (2024)
- [Redactor: A Data-centric and Individualized Defense Against Inference Attacks](https://mlsanity.com/paper/2202.02902/) (2022)
- [Privacy protection based on mask template](https://mlsanity.com/paper/2202.06250/) (2022)
- [VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints](https://mlsanity.com/paper/2310.10656/) (2023)
- [Model Copyright Protection in Buyer-seller Environment](https://mlsanity.com/paper/2312.05262/) (2023)

## Abstract (arXiv)

Deep neural networks have had enormous impact on various domains of computer science, considerably outperforming previous state of the art machine learning techniques. To achieve this performance, neural networks need large quantities of data and huge computational resources, which heavily increases their construction costs. The increased cost of building a good deep neural network model gives rise to a need for protecting this investment from potential copyright infringements. Legitimate owners of a machine learning model want to be able to reliably track and detect a malicious adversary that tries to steal the intellectual property related to the model. Recently, this problem was tackled by introducing in deep neural networks the concept of watermarking, which allows a legitimate owner to embed some secret information(watermark) in a given model. The watermark allows the legitimate owner to detect copyright infringements of his model. This paper focuses on verifying the robustness and reliability of state-of- the-art deep neural network watermarking schemes. We show that, a malicious adversary, even in scenarios where the watermark is difficult to remove, can still evade the verification by the legitimate owners, thus avoiding the detection of model theft.