TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding

February 12, 2022 Β· Declared Dead Β· πŸ› Asia-Pacific Computer Systems Architecture Conference

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Giulio Pagnotta, Dorjan Hitaj, Briland Hitaj, Fernando Perez-Cruz, Luigi V. Mancini arXiv ID 2202.06091 Category cs.CR: Cryptography & Security Cross-listed cs.IT, cs.LG Citations 11 Venue Asia-Pacific Computer Systems Architecture Conference Last Checked 4 months ago
Abstract
Watermarking of deep neural networks (DNNs) has gained significant traction in recent years, with numerous (watermarking) strategies being proposed as mechanisms that can help verify the ownership of a DNN in scenarios where these models are obtained without the permission of the owner. However, a growing body of work has demonstrated that existing watermarking mechanisms are highly susceptible to removal techniques, such as fine-tuning, parameter pruning, or shuffling. In this paper, we build upon extensive prior work on covert (military) communication and propose TATTOOED, a novel DNN watermarking technique that is robust to existing threats. We demonstrate that using TATTOOED as their watermarking mechanisms, the DNN owner can successfully obtain the watermark and verify model ownership even in scenarios where 99% of model parameters are altered. Furthermore, we show that TATTOOED is easy to employ in training pipelines, and has negligible impact on model performance.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Cryptography & Security

Died the same way β€” πŸ‘» Ghosted