mlsanityData to 7 Oct 2026

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons

arXiv 2402.04325 ↗First posted 6 Feb 2024cs.LG cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making. Despite their transforming impact, DNNs face two critical challenges: the vulnerability to adversarial attacks and the increasing computational costs associated with more complex and larger models. In this paper, we introduce an effective method designed to simultaneously enhance adversarial robustness and execution efficiency. Unlike prior studies that enhance robustness via uniformly injecting noise, we introduce a non-uniform noise injection algorithm, strategically applied at each DNN layer to disrupt adversarial perturbations introduced in attacks. By employing approximation techniques, our approach identifies and protects essential neurons while strategically introducing noise into non-essential neurons. Our experimental results demonstrate that our method successfully enhances both robustness and efficiency across several attack scenarios, model architectures, and datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2016Wide Residual Networkscited by 3,057
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  8. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  9. 2016Adversarial examples in the physical worldcited by 1,762
  10. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  11. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  12. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
23 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  2. 2019Adversarial Training for Free!cited by 638
  3. 2020Overfitting in adversarially robust deep learningcited by 504
  4. 2020Efficient Content-Based Sparse Attention with Routing Transformerscited by 469
  5. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  6. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  7. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  8. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  9. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  10. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 156
  11. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 123
  12. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  13. 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 75
  14. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 73
  15. 2018Sparse DNNs with Improved Adversarial Robustnesscited by 71
  16. 2019Model Compression with Adversarial Robustness: A Unified Optimization Frameworkcited by 71
  17. 2019Enhancing Adversarial Defense by k-Winners-Take-Allcited by 51
  18. 2019Theoretical evidence for adversarial robustness through randomizationcited by 33
  19. 2019Deep Multi-Sensor Lane Detectioncited by 30
  20. 2021Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networkscited by 29
  21. 2020Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustnesscited by 27
  22. 2018Dynamic Sparse Graph for Efficient Deep Learningcited by 18
  23. 2018Combating Adversarial Attacks Using Sparse Representationscited by 9

Built on by

Not cited yet.