mlsanityData to 7 Oct 2026

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method

arXiv 2306.02021 ↗First posted 3 Jun 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract considerable attention in adversarial example detection. In this paper, we fill this gap by positioning the problem of black-box adversarial example detection (BAD). Data analysis under the introduced BAD settings demonstrates (1) the incapability of existing detectors in addressing the black-box scenario and (2) the potential of exploring BAD solutions from a data perspective. To tackle the BAD problem, we propose a data reconstruction-based adversarial example detection method. Specifically, we use variational auto-encoder (VAE) to capture both pixel and frequency representations of normal examples. Then we use reconstruction error to detect adversarial examples. Compared with existing detection methods, the proposed method achieves substantially better detection performance in BAD, which helps promote the deployment of adversarial example detection-based defense solutions in real-world models.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 3 Jun 2023.

Builds on

27 of 33 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2016Wide Residual Networkscited by 3,057
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
15 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  3. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  4. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  5. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  6. 2017Detecting Adversarial Samples from Artifactscited by 244
  7. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  8. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  9. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 70
  10. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  11. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  12. 2022Transferable Adversarial Attack based on Integrated Gradientscited by 35
  13. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  14. 2019Interpreting Adversarial Examples by Activation Promotion and Suppressioncited by 17
  15. 2019Learning Competitive and Discriminative Reconstructions for Anomaly Detectioncited by 9

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Featurescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Adversarial defense based on distribution transfer
  2. 2023Adversarial Examples Are Not Real Features
  3. 2024CausAdv: A Causal-based Framework for Detecting Adversarial Examples
  4. 2023Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models
  5. 2024Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
  6. 2023Latent Magic: An Investigation into Adversarial Examples Crafted in the Semantic Latent Space
  7. 2024Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
  8. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attacks