SpikeTimer: Exploring Active Copyright Protection in Spiking Neural Networks via Temporal Backdoor Regularization

2026-06-25

AI Summary

This work addresses the lack of copyright protection mechanisms for spiking neural networks (SNNs), which stems from the complexity of temporal coding. The authors propose SpikeTimer, a novel framework that introduces the first time-dependent authorization scheme: neuromorphic inputs are partitioned into temporal segments, and authentication tokens are embedded exclusively within authorized time windows, enabling the model to respond correctly only to inputs containing valid temporal tokens. Leveraging SNNs’ intrinsic temporal segmentation properties, this approach supports multi-user authorization and flexible token embedding. Temporal backdoor regularization and robust training strategies further enhance resistance against adversarial attacks. Experiments across multiple neuromorphic datasets demonstrate that authorized inputs suffer only a ~1.5% accuracy drop, while unauthorized inputs degrade to ~10% accuracy, with strong robustness preserved against fine-tuning and pruning attacks.

Abstract

Spiking Neural Networks (SNN) have emerged as a revolutionary paradigm compared to traditional Deep Neural Networks (DNN) in energy-efficient computing, showcasing exceptional capabilities in processing event-driven sensory data for real-time applications like robotics and edge AI systems. However, unlike extensive studies on DNN copyright solutions, SNN copyright protection remains largely underexplored due to their inherent temporal coding complexities and spike-driven computation. In this study, we propose a novel active copyright protection framework named SpikeTimer for SNNs via temporal backdoor learning. SpikeTimer partitions neuromorphic data into designated timeslices and exclusively embeds authorized tokens within authorized slices. Furthermore, the inherent temporal segmentation characteristic intrinsically enables SpikeTimer to support multi-user authorization mechanisms and accommodates token embedding of arbitrary morphology. Based on this, SpikeTimer precisely responds to authorized data containing a token within the correct timeslice, while producing erroneous responses to unauthorized data. Our key innovation lies in establishing a time-dependent authorization mechanism that protects the SNN copyright by temporal token validity. Additionally, SpikeTimer retains its defensive efficacy even under adversarial attempts. Evaluations on multiple neuromorphic datasets manifest that SpikeTimer achieves around 10% accuracy on unauthorized data with merely around 1.5% degradation on authorized inputs. Moreover, SpikeTimer demonstrates robust resistance against model finetuning and pruning threats.

Problem

• Spiking Neural Networks
• Copyright Protection
• Temporal Coding
• Backdoor Learning
• Neuromorphic Computing

Innovation

• Spiking Neural Networks
• Temporal Backdoor
• Copyright Protection
• Time-dependent Authorization
• Neuromorphic Computing