mlsanityData to 7 Oct 2026

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples

arXiv 2102.04150 ↗First posted 8 Feb 2021cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial samples. In recent years, numerous studies have been conducted in this new area called "Adversarial Machine Learning" to devise new adversarial attacks and to defend against these attacks with more robust DNN architectures. However, almost all the research work so far has been concentrated on utilising model loss function to craft adversarial examples or create robust models. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes by which we perturb the input to the areas where the model has not seen before. We proposed new attack ideas based on the epistemic uncertainty of the model. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.40%, 82.86% to 89.92% and 88.06% to 90.03% on MNIST Digit, MNIST Fashion and CIFAR-10 datasets, respectively.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 33 of its 60 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

33 of 60 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2017On Calibration of Modern Neural Networkscited by 4,860
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  9. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
21 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  3. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2015Weight Uncertainty in Neural Networkscited by 554
  6. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  7. 2018Universality of Deep Convolutional Neural Networkscited by 176
  8. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  9. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  10. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  11. 2013Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networkscited by 84
  12. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 61
  13. 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
  14. 2020Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detectioncited by 46
  15. 2019Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forwardcited by 33
  16. 2019Fooling a Real Car with Adversarial Traffic Signscited by 29
  17. 2018Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictionscited by 25
  18. 2018Adversarial Examples - A Complete Characterisation of the Phenomenoncited by 11
  19. 2020Closeness and Uncertainty Aware Adversarial Examples Detection in Adversarial Machine Learningcited by 6
  20. 2019Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Casescited by 5
  21. 2020A Generative Model based Adversarial Security of Deep Learning and Linear Classifier Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

12 papers.

  1. 2024SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Modelscited by 54
  2. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  3. 2021Attribution of Predictive Uncertainties in Classification Modelscited by 8
  4. 2025Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Modelscited by 6
  5. 2021Adversarial Machine Learning Security Problems for 6G: mmWave Beam Prediction Use-Casecited by 5
  6. 2021Security Concerns on Machine Learning Solutions for 6G Networks in mmWave Beam Predictioncited by 5
  7. 2022The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retrainingcited by 3
  8. 2022Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless Networkscited by 2
  9. 2022Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustnesscited by 1
  10. 2023Practical Adversarial Attacks Against AI-Driven Power Allocation in a Distributed MIMO Networkcited by 0
  11. 2024Relationship between Uncertainty in DNNs and Adversarial Attackscited by 0
  12. 2026AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensorscited by 0