mlsanityData to 7 Oct 2026

Adversarial Examples Detection beyond Image Space

arXiv 2102.11586 ↗First posted 23 Feb 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have been proposed. However, most of them perform poorly on detecting adversarial examples with extremely slight perturbations. By exploring these adversarial examples, we find that there exists compliance between perturbations and prediction confidence, which guides us to detect few-perturbation attacks from the aspect of prediction confidence. To detect both few-perturbation attacks and large-perturbation attacks, we propose a method beyond image space by a two-stream architecture, in which the image stream focuses on the pixel artifacts and the gradient stream copes with the confidence artifacts. The experimental results show that the proposed method outperforms the existing methods under oblivious attacks and is verified effective to defend omniscient attacks as well.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 23 Feb 2021.

Builds on

18 of 25 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  7. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  8. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  9. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  10. 2017Detecting Adversarial Samples from Artifactscited by 244
  11. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  12. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
6 more
  1. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  2. 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
  3. 2017Is Second-order Information Helpful for Large-scale Visual Recognition?cited by 44
  4. 2018Detection based Defense against Adversarial Examples from the Steganalysis Point of Viewcited by 32
  5. 2018Defending Against Universal Perturbations With Shared Adversarial Trainingcited by 25
  6. 2018Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networkscited by 21

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 1.

5 papers.

  1. 2023Dynamic Adversarial Attacks on Autonomous Driving Systemscited by 11
  2. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  3. 2022Randomized Smoothing under Attack: How Good is it in Pratice?cited by 7
  4. 2022Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbationscited by 0
  5. 2024Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustnesscited by 0