mlsanityData to 7 Oct 2026

Enhancing Adversarial Robustness in SNNs with Sparse Gradients

arXiv 2405.20355 ↗First posted 30 May 2024cs.NE cs.CR cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) have attracted great attention for their energy-efficient operations and biologically inspired structures, offering potential advantages over Artificial Neural Networks (ANNs) in terms of energy efficiency and interpretability. Nonetheless, similar to ANNs, the robustness of SNNs remains a challenge, especially when facing adversarial attacks. Existing techniques, whether adapted from ANNs or specifically designed for SNNs, exhibit limitations in training SNNs or defending against strong attacks. In this paper, we propose a novel approach to enhance the robustness of SNNs through gradient sparsity regularization. We observe that SNNs exhibit greater resilience to random perturbations compared to adversarial perturbations, even at larger scales. Motivated by this, we aim to narrow the gap between SNNs under adversarial and random perturbations, thereby improving their overall robustness. To achieve this, we theoretically prove that this performance gap is upper bounded by the gradient sparsity of the probability associated with the true label concerning the input image, laying the groundwork for a practical strategy to train robust SNNs by regularizing the gradient sparsity. We validate the effectiveness of our approach through extensive experiments on both image-based and event-based datasets. The results demonstrate notable improvements in the robustness of SNNs. Our work highlights the importance of gradient sparsity in SNNs and its role in enhancing robustness.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 49 of its 78 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

49 of 78 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2016Wide Residual Networkscited by 3,057
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2018Robustness May Be at Odds with Accuracycited by 873
  10. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  11. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  12. 2016The Mythos of Model Interpretabilitycited by 716
37 more
  1. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  3. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  4. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  5. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  6. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  7. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  8. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  9. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  10. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  11. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  12. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  13. 2017Deep Rewiring: Training very sparse deep networkscited by 136
  14. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
  15. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 119
  16. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 116
  17. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  18. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  19. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  20. 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
  21. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  22. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 68
  23. 2022GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 63
  24. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 61
  25. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 47
  26. 2019Scaleable input gradient regularization for adversarial robustnesscited by 45
  27. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 38
  28. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 35
  29. 2020Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradientcited by 31
  30. 2022Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?cited by 24
  31. 2023ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networkscited by 22
  32. 2021DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networkscited by 21
  33. 2020TCL: an ANN-to-SNN Conversion with Trainable Clipping Layerscited by 20
  34. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12
  35. 2022Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examplescited by 12
  36. 2021R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensorscited by 9
  37. 2023Adversarially Robust Spiking Neural Networks Through Conversioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradientscited by 9
  2. 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networkscited by 5
  3. 2025MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularizationcited by 2
  4. 2025Adversarially Robust Spiking Neural Networks with Sparse Connectivitycited by 0
  5. 2025Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemblecited by 0
  6. 2025Quantifying How Training Gradient Sparsity Affect Spiking Neural Network Accuracy And Robustnesscited by 0
  7. 2025Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networkscited by 0
  8. 2026Robust Spiking Neural Networks Against Adversarial Attackscited by 0
  9. 2026Fluently Lying: Adversarial Robustness Can Be Substrate-Dependentcited by 0