A Novel Noise Injection-based Training Scheme for Better Model Robustness
Not on the map. Why?
Abstract (arXiv)
Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-based training scheme for better model robustness. Specifically, we first develop a likelihood ratio method to estimate the gradient with respect to both synaptic weights and noise levels for stochastic gradient descent training. Then, we design an approximation for the vanilla noise injection-based training method to reduce memory and improve computational efficiency. Next, we apply our proposed scheme to spiking neural networks and evaluate the performance of classification accuracy and robustness on MNIST and Fashion-MNIST datasets. Experiment results show that our proposed method achieves a much better performance on adversarial robustness and slightly better performance on original accuracy, compared with the conventional gradient-based training method.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 17 Feb 2023.
Builds on
28 of 58 references.
References · 28
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
- 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
- 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
- 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
- 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
16 more
- 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
- 2018Physical Adversarial Examples for Object Detectorscited by 163
- 2014Difference Target Propagationcited by 144
- 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
- 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
- 2021Triangle Attack: A Query-efficient Decision-based Adversarial Attackcited by 48
- 2018Biologically Motivated Algorithms for Propagating Local Target Representationscited by 43
- 2019Robustness of Neural Networks: A Probabilistic and Practical Approachcited by 38
- 2019Query-efficient Meta Attack to Deep Neural Networkscited by 33
- 2020Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systemscited by 26
- 2018Adversarial Noise Layer: Regularize Neural Network By Adding Noisecited by 25
- 2019Spiking Neural Predictive Coding for Continual Learning from Data Streamscited by 17
- 2019Yet another but more efficient black-box adversarial attack: tiling and evolution strategiescited by 17
- 2021Noise Optimization for Artificial Neural Networkscited by 7
- 2020A Modeled Approach for Online Adversarial Test of Operational Vehicle Safety (extended version)cited by 4
- 2019Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verificationcited by 3
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.