mlsanityData to 14 Oct 2026

Investigating Weight-Perturbed Deep Neural Networks With Application in Iris Presentation Attack Detection

arXiv 2311.12764 ↗First posted 21 Nov 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) exhibit superior performance in various machine learning tasks, e.g., image classification, speech recognition, biometric recognition, object detection, etc. However, it is essential to analyze their sensitivity to parameter perturbations before deploying them in real-world applications. In this work, we assess the sensitivity of DNNs against perturbations to their weight and bias parameters. The sensitivity analysis involves three DNN architectures (VGG, ResNet, and DenseNet), three types of parameter perturbations (Gaussian noise, weight zeroing, and weight scaling), and two settings (entire network and layer-wise). We perform experiments in the context of iris presentation attack detection and evaluate on two publicly available datasets: LivDet-Iris-2017 and LivDet-Iris-2020. Based on the sensitivity analysis, we propose improved models simply by perturbing parameters of the network without undergoing training. We further combine these perturbed models at the score-level and at the parameter-level to improve the performance over the original model. The ensemble at the parameter-level shows an average improvement of 43.58% on the LivDet-Iris-2017 dataset and 9.25% on the LivDet-Iris-2020 dataset. The source code is available at https://github.com/redwankarimsony/WeightPerturbation-MSU.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 21 Nov 2023.

Builds on

18 of 31 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2016Universal adversarial perturbationscited by 784
  9. 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 189
  10. 2016Robustness of classifiers: from adversarial to random noisecited by 88
  11. 2020Can Adversarial Weight Perturbations Inject Neural Backdoors?cited by 56
  12. 2019Post-mortem Iris Recognition with Deep-Learning-based Image Segmentationcited by 32
6 more
  1. 2020Iris Liveness Detection Competition (LivDet-Iris) -- The 2020 Editioncited by 27
  2. 2020D-NetPAD: An Explainable and Interpretable Iris Presentation Attack Detectorcited by 26
  3. 2021Formalizing Generalization and Robustness of Neural Networks to Weight Perturbationscited by 22
  4. 2017On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbationscited by 14
  5. 2019Sensitivity Analysis of Deep Neural Networkscited by 6
  6. 2015An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variabilitycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detectioncited by 4
  2. 2026APEX: Probing Neural Networks via Activation Perturbationcited by 1
  3. 2024RW-NSGCN: A Robust Approach to Structural Attacks via Negative Samplingcited by 0