TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 41 of its 81 references that are in the map. First posted on arXiv 12 Feb 2022.
Builds on
41 of 81 references.
References · 41
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016Pointer Sentinel Mixture Modelscited by 2,992
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2014FitNets: Hints for Thin Deep Netscited by 1,619
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
29 more
- 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
- 2016Stealing Machine Learning Models via Prediction APIscited by 602
- 2018Invertible Residual Networkscited by 364
- 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
- 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
- 2017Embedding Watermarks into Deep Neural Networkscited by 227
- 2015Quantized Convolutional Neural Networks for Mobile Devicescited by 212
- 2017Machine Learning Models that Remember Too Muchcited by 165
- 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
- 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
- 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 94
- 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
- 2018Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscalingcited by 74
- 2021A survey of deep neural network watermarking techniquescited by 69
- 2019Robust Watermarking of Neural Network with Exponential Weightingcited by 48
- 2019REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Datacited by 40
- 2018Digital Watermarking for Deep Neural Networkscited by 37
- 2017PassGAN: A Deep Learning Approach for Password Guessingcited by 25
- 2019BlackMarks: Blackbox Multibit Watermarking for Deep Neural Networkscited by 25
- 2016Ask the GRU: Multi-Task Learning for Deep Text Recommendationscited by 24
- 2020Spread-Transform Dither Modulation Watermarking of Deep Neural Networkcited by 23
- 2019Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarkingcited by 11
- 2021PassFlow: Guessing Passwords with Generative Flowscited by 10
- 2019The Naked Sun: Malicious Cooperation Between Benign-Looking Processescited by 8
- 2021Reliable Detection of Compressed and Encrypted Datacited by 7
- 2021MalPhase: Fine-Grained Malware Detection Using Network Flow Datacited by 7
- 2020EnCoD: Distinguishing Compressed and Encrypted File Fragmentscited by 5
- 2019A novel method for identifying the deep neural network model with the Serial Numbercited by 4
- 2022FedComm: Federated Learning as a Medium for Covert Communicationcited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1; 2026: 1.
3 papers.