mlsanityData to 7 Oct 2026

Robust Spiking Neural Networks Against Adversarial Attacks

arXiv 2602.20548 ↗First posted 24 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments remains significantly constrained. In this study, we theoretically demonstrate that those threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs. We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances. To address this challenge, we propose a Threshold Guarding Optimization (TGO) method, which comprises two key aspects. First, we incorporate additional constraints into the loss function to move neurons' membrane potentials away from their thresholds. It increases SNNs' gradient sparsity, thereby reducing the theoretical upper bound of adversarial attacks. Second, we introduce noisy spiking neurons to transition the neuronal firing mechanism from deterministic to probabilistic, decreasing their state-flipping probability due to minor disturbances. Extensive experiments conducted in standard adversarial scenarios prove that our method significantly enhances the robustness of directly trained SNNs. These findings pave the way for advancing more reliable and secure neuromorphic computing in real-world applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 81 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

44 of 81 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  5. 2018Robustness May Be at Odds with Accuracycited by 873
  6. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  7. 2019Adversarial Training for Free!cited by 638
  8. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  9. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  10. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  11. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  12. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
32 more
  1. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  2. 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 223
  3. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  4. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  5. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  6. 2023Spike-driven Transformercited by 141
  7. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 119
  8. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 70
  9. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 68
  10. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 61
  11. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 47
  12. 2024QKFormer: Hierarchical Spiking Transformer using Q-K Attentioncited by 46
  13. 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
  14. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  15. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  16. 2024SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networkscited by 38
  17. 2018A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rulecited by 36
  18. 2020Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradientcited by 31
  19. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
  20. 2016Challenges and Opportunities in Edge Computingcited by 26
  21. 2023Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learningcited by 22
  22. 2025Spiking Vision Transformer with Saccadic Attentioncited by 21
  23. 2022Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Networkcited by 19
  24. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12
  25. 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradientscited by 9
  26. 2024Robust Stable Spiking Neural Networkscited by 9
  27. 2024Ternary Spike-based Neuromorphic Signal Processing Systemcited by 8
  28. 2025Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modelingcited by 2
  29. 2025MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularizationcited by 2
  30. 2025BSO: Binary Spiking Online Optimization Algorithmcited by 2
  31. 2021CBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier methodcited by 1
  32. 2023Spike timing reshapes robustness against attacks in spiking neural networkscited by 1

Built on by

Not cited yet.