mlsanityData to 14 Oct 2026

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks

arXiv 1905.02704 ↗First posted 7 May 2019cs.NE cs.LG eess.SPcited by 36

Not on the map. Why?

Abstract (arXiv)

In this era of machine learning models, their functionality is being threatened by adversarial attacks. In the face of this struggle for making artificial neural networks robust, finding a model, resilient to these attacks, is very important. In this work, we present, for the first time, a comprehensive analysis of the behavior of more bio-plausible networks, namely Spiking Neural Network (SNN) under state-of-the-art adversarial tests. We perform a comparative study of the accuracy degradation between conventional VGG-9 Artificial Neural Network (ANN) and equivalent spiking network with CIFAR-10 dataset in both whitebox and blackbox setting for different types of single-step and multi-step FGSM (Fast Gradient Sign Method) attacks. We demonstrate that SNNs tend to show more resiliency compared to ANN under black-box attack scenario. Additionally, we find that SNN robustness is largely dependent on the corresponding training mechanism. We observe that SNNs trained by spike-based backpropagation are more adversarially robust than the ones obtained by ANN-to-SNN conversion rules in several whitebox and blackbox scenarios. Finally, we also propose a simple, yet, effective framework for crafting adversarial attacks from SNNs. Our results suggest that attacks crafted from SNNs following our proposed method are much stronger than those crafted from ANNs.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 5; 2024: 5; 2025: 10; 2026: 4.

36 papers.

Sort:

By area:

  1. 2021Visual Explanations from Spiking Neural Networks using Interspike Intervalscited by 27
  2. 2021DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networkscited by 21
  3. 2022Deep Reinforcement Learning with Spiking Q-learningcited by 18
  4. 2022Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examplescited by 13
  5. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12
  6. 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradientscited by 10
  7. 2021R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensorscited by 9
  8. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 9
  9. 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradientscited by 9
  10. 2023Adversarially Robust Spiking Neural Networks Through Conversioncited by 7
  11. 2022Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systemscited by 6
  12. 2023Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representationcited by 6
24 more
  1. 2025Input-Triggered Hardware Trojan Attack on Spiking Neural Networkscited by 5
  2. 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networkscited by 5
  3. 2022Navigating Local Minima in Quantized Spiking Neural Networkscited by 4
  4. 2024Time-Distributed Backdoor Attacks on Federated Spiking Learningcited by 4
  5. 2022Spiking Approximations of the MaxPooling Operation in Deep SNNscited by 3
  6. 2023HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholdscited by 3
  7. 2024Membership Privacy Evaluation in Deep Spiking Neural Networkscited by 3
  8. 2024Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Camerascited by 3
  9. 2024Benchmarking Spiking Neural Network Learning Methods with Varying Localitycited by 2
  10. 2025MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularizationcited by 2
  11. 2022Adversarial Defense via Neural Oscillation inspired Gradient Maskingcited by 1
  12. 2025On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysiscited by 1
  13. 2025Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domaincited by 1
  14. 2022Biologically Plausible Variational Policy Gradient with Spiking Recurrent Winner-Take-All Networkscited by 0
  15. 2023HyperSNN: A new efficient and robust deep learning model for resource constrained control applicationscited by 0
  16. 2023Feature Attribution Explanations for Spiking Neural Networkscited by 0
  17. 2025On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learningcited by 0
  18. 2025Izhikevich-Inspired Temporal Dynamics for Enhancing Privacy, Efficiency, and Transferability in Spiking Neural Networkscited by 0
  19. 2025Adversarially Robust Spiking Neural Networks with Sparse Connectivitycited by 0
  20. 2025RBA-FE: A Robust Brain-Inspired Audio Feature Extractor for Depression Diagnosiscited by 0
  21. 2025Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagationcited by 0
  22. 2026Fluently Lying: Adversarial Robustness Can Be Substrate-Dependentcited by 0
  23. 2026Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attackscited by 0
  24. 2026Controllable Stochastic Quantization Encoding for Adversarially Robust Spiking Neural Networkscited by 0