mlsanityData to 14 Oct 2026

HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds

arXiv 2308.10373 ↗First posted 20 Aug 2023cs.NE cs.CR cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

While spiking neural networks (SNNs) offer a promising neurally-inspired model of computation, they are vulnerable to adversarial attacks. We present the first study that draws inspiration from neural homeostasis to design a threshold-adapting leaky integrate-and-fire (TA-LIF) neuron model and utilize TA-LIF neurons to construct the adversarially robust homeostatic SNNs (HoSNNs) for improved robustness. The TA-LIF model incorporates a self-stabilizing dynamic thresholding mechanism, offering a local feedback control solution to the minimization of each neuron's membrane potential error caused by adversarial disturbance. Theoretical analysis demonstrates favorable dynamic properties of TA-LIF neurons in terms of the bounded-input bounded-output stability and suppressed time growth of membrane potential error, underscoring their superior robustness compared with the standard LIF neurons. When trained with weak FGSM attacks (attack budget = 2/255) and tested with much stronger PGD attacks (attack budget = 8/255), our HoSNNs significantly improve model accuracy on several datasets: from 30.54% to 74.91% on FashionMNIST, from 0.44% to 35.06% on SVHN, from 0.56% to 42.63% on CIFAR10, from 0.04% to 16.66% on CIFAR100, over the conventional LIF-based SNNs.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 40 of its 87 references that are in the map. First posted on arXiv 20 Aug 2023.

Builds on

40 of 87 references.

References · 40

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  12. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
28 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  2. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  3. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  4. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  5. 2019On Evaluating Adversarial Robustnesscited by 447
  6. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
  7. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  8. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  9. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  10. 2018Adversarial Attacks and Defences: A Surveycited by 259
  11. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 243
  12. 2017On Detecting Adversarial Perturbationscited by 232
  13. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  14. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 123
  15. 2019Adversarial Examples Are a Natural Consequence of Test Error in Noisecited by 114
  16. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 100
  17. 2016Robustness of classifiers: from adversarial to random noisecited by 88
  18. 2020Opportunities and Challenges in Deep Learning Adversarial Robustness: A Surveycited by 72
  19. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 65
  20. 2019Adversarial Defense by Restricting the Hidden Space of Deep Neural Networkscited by 56
  21. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 48
  22. 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 48
  23. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 36
  24. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
  25. 2019Rapid online learning and robust recall in a neuromorphic olfactory circuitcited by 18
  26. 2020Towards Understanding the Effect of Leak in Spiking Neural Networkscited by 15
  27. 2022Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examplescited by 13
  28. 2022Toward Robust Spiking Neural Network Against Adversarial Perturbationcited by 12

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Camerascited by 3
  2. 2024Robust and Efficient Adversarial Defense in SNNs via Image Purification and Joint Detectioncited by 2
  3. 2025Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periodscited by 0