Watermarking Neuromorphic Brains: Intellectual Property Protection in Spiking Neural Networks
Not on the map. Why?
Abstract (arXiv)
As spiking neural networks (SNNs) gain traction in deploying neuromorphic computing solutions, protecting their intellectual property (IP) has become crucial. Without adequate safeguards, proprietary SNN architectures are at risk of theft, replication, or misuse, which could lead to significant financial losses for the owners. While IP protection techniques have been extensively explored for artificial neural networks (ANNs), their applicability and effectiveness for the unique characteristics of SNNs remain largely unexplored. In this work, we pioneer an investigation into adapting two prominent watermarking approaches, namely, fingerprint-based and backdoor-based mechanisms to secure proprietary SNN architectures. We conduct thorough experiments to evaluate the impact on fidelity, resilience against overwrite threats, and resistance to compression attacks when applying these watermarking techniques to SNNs, drawing comparisons with their ANN counterparts. This study lays the groundwork for developing neuromorphic-aware IP protection strategies tailored to the distinctive dynamics of SNNs.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 7 May 2024.
Builds on
16 of 30 references.
References · 16
- 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
- 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
- 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
- 2017Embedding Watermarks into Deep Neural Networkscited by 248
- 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
- 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 118
- 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 100
- 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 93
- 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 88
- 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 48
- 2019EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Camerascited by 46
- 2020Brain-Inspired Learning on Neuromorphic Substratescited by 37
4 more
- 2020Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluationscited by 31
- 2019Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognitioncited by 27
- 2022Recent Advances and New Frontiers in Spiking Neural Networkscited by 10
- 2024BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attackscited by 7
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024Are Neuromorphic Architectures Inherently Privacy-preserving? An Exploratory Study
- 2022Cracking White-box DNN Watermarks via Invariant Neuron Transforms
- 2023Deep Intellectual Property Protection: A Survey
- 2026SpikeTimer: Exploring Active Copyright Protection in Spiking Neural Networks via Temporal Backdoor Regularization
- 2023Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
- 2021Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images
- 2025Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluation
- 2021Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks