mlsanityData to 7 Oct 2026

Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions

arXiv 2103.11002 ↗First posted 19 Mar 2021cs.CR cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks will aid in recovering the tools and processes used in these attacks. In this paper, we present two techniques that support automated identification and attribution of adversarial ML attack toolchains using Co-occurrence Pixel statistics and Laplacian Residuals. Our experiments show that the proposed techniques can identify parameters used to generate adversarial samples. To the best of our knowledge, this is the first approach to attribute gradient based adversarial attacks and estimate their parameters. Source code and data is available at: https://github.com/michael-goebel/ei_red

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 28 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

18 of 28 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  4. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  5. 2017Detecting Adversarial Samples from Artifactscited by 244
  6. 2017On Detecting Adversarial Perturbationscited by 232
  7. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  8. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  9. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  10. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  11. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  12. 2016Measuring Neural Net Robustness with Constraintscited by 90
6 more
  1. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  2. 2015Learning with a Strong Adversarycited by 68
  3. 2017Adversarial and Clean Data Are Not Twinscited by 52
  4. 2016Early Methods for Detecting Adversarial Imagescited by 36
  5. 2016Adversarial Diversity and Hard Positive Generationcited by 35
  6. 2015Robust Convolutional Neural Networks under Adversarial Noisecited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2023Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Networkcited by 8
  2. 2023Can Adversarial Examples Be Parsed to Reveal Victim Model Information?cited by 1
  3. 2023A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptionscited by 0
  4. 2026Identifying Adversary Characteristics from an Observed Attackcited by 0