mlsanityData to 14 Oct 2026

Adversarially Robust Spiking Neural Networks with Sparse Connectivity

arXiv 2505.15833 ↗First posted 16 May 2025cs.NE cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further ensure the reliability of these systems against malicious actors, recent works have extensively studied adversarial robustness of existing architectures. Our work focuses on the intersection of adversarial robustness, memory- and energy-efficiency in neural networks. We introduce a neural network conversion algorithm designed to produce sparse and adversarially robust spiking neural networks (SNNs) by leveraging the sparse connectivity and weights from a robustly pretrained artificial neural network (ANN). Our approach combines the energy-efficient architecture of SNNs with a novel conversion algorithm, leading to state-of-the-art performance with enhanced energy and memory efficiency through sparse connectivity and activations. Our models are shown to achieve up to 100x reduction in the number of weights to be stored in memory, with an estimated 8.6x increase in energy efficiency compared to dense SNNs, while maintaining high performance and robustness against adversarial threats.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 63 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

45 of 63 references.

References · 45

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Wide Residual Networkscited by 3,070
  6. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  12. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
33 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  2. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  3. 2019On Evaluating Adversarial Robustnesscited by 447
  4. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  5. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  6. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  7. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
  8. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  9. 2019What's Hidden in a Randomly Weighted Neural Network?cited by 237
  10. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  11. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  12. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 144
  13. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 123
  14. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  15. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 65
  16. 2021Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracycited by 62
  17. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 48
  18. 2021Consistency Regularization for Adversarial Robustnesscited by 42
  19. 2017Security Evaluation of Pattern Classifiers under Attackcited by 39
  20. 2019Adversarial Robustness May Be at Odds With Simplicitycited by 39
  21. 2020Exploring the Connection Between Binary and Spiking Neural Networkscited by 38
  22. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 36
  23. 2020Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradientcited by 31
  24. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
  25. 2021DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networkscited by 21
  26. 2023Workload-Balanced Pruning for Sparse Spiking Neural Networkscited by 15
  27. 2021Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based Visioncited by 14
  28. 2022Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examplescited by 13
  29. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12
  30. 2024Robust Stable Spiking Neural Networkscited by 11
  31. 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradientscited by 10
  32. 2023Adversarially Robust Spiking Neural Networks Through Conversioncited by 7
  33. 2024Holistic Adversarially Robust Pruningcited by 5

Built on by

Not cited yet.