mlsanityData to 14 Oct 2026

Self-Healing Robust Neural Networks via Closed-Loop Control

arXiv 2206.12963 ↗First posted 26 Jun 2022cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Despite the wide applications of neural networks, there have been increasing concerns about their vulnerability issue. While numerous attack and defense techniques have been developed, this work investigates the robustness issue from a new angle: can we design a self-healing neural network that can automatically detect and fix the vulnerability issue by itself? A typical self-healing mechanism is the immune system of a human body. This biology-inspired idea has been used in many engineering designs but is rarely investigated in deep learning. This paper considers the post-training self-healing of a neural network, and proposes a closed-loop control formulation to automatically detect and fix the errors caused by various attacks or perturbations. We provide a margin-based analysis to explain how this formulation can improve the robustness of a classifier. To speed up the inference of the proposed self-healing network, we solve the control problem via improving the Pontryagin Maximum Principle-based solver. Lastly, we present an error estimation of the proposed framework for neural networks with nonlinear activation functions. We validate the performance on several network architectures against various perturbations. Since the self-healing method does not need a-priori information about data perturbations/attacks, it can handle a broad class of unforeseen perturbations.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 33 of its 66 references that are in the map. First posted on arXiv 26 Jun 2022.

Builds on

33 of 66 references.

References · 33

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2018Neural Ordinary Differential Equationscited by 3,779
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  12. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
21 more
  1. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  2. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  3. 2017Countering Adversarial Images using Input Transformationscited by 520
  4. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
  5. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  6. 2017Stable Architectures for Deep Neural Networkscited by 341
  7. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  8. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  9. 2020Large-Scale Adversarial Training for Vision-and-Language Representation Learningcited by 327
  10. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
  11. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  12. 2020Feature Purification: How Adversarial Training Performs Robust Deep Learningcited by 107
  13. 2021Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackscited by 91
  14. 2017Maximum Principle Based Algorithms for Deep Learningcited by 78
  15. 2020Efficient Exact Verification of Binarized Neural Networkscited by 33
  16. 2021Towards Robust Neural Networks via Close-loop Controlcited by 23
  17. 2021RAILS: A Robust Adversarial Immune-inspired Learning Systemcited by 8
  18. 2018Fault Tolerance in Iterative-Convergent Machine Learningcited by 7
  19. 2019Chance-Constrained and Yield-aware Optimization of Photonic ICs with Non-Gaussian Correlated Process Variationscited by 1
  20. 2021Immuno-mimetic Deep Neural Networks (Immuno-Net)cited by 1
  21. 2021PoBO: A Polynomial Bounding Method for Chance-Constrained Yield-Aware Optimization of Photonic ICscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2024PID Control-Based Self-Healing to Improve the Robustness of Large Language Modelscited by 3
  2. 2024Mitigating distribution shift in machine learning-augmented hybrid simulationcited by 2
  3. 2023Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspectivecited by 1
  4. 2025NAPER: Fault Protection for Real-Time Resource-Constrained Deep Neural Networkscited by 1
  5. 2026State-space models through the lens of ensemble controlcited by 0