mlsanityData to 7 Oct 2026

Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples

arXiv 2107.00561 ↗First posted 1 Jul 2021cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

We present DeClaW, a system for detecting, classifying, and warning of adversarial inputs presented to a classification neural network. In contrast to current state-of-the-art methods that, given an input, detect whether an input is clean or adversarial, we aim to also identify the types of adversarial attack (e.g., PGD, Carlini-Wagner or clean). To achieve this, we extract statistical profiles, which we term as anomaly feature vectors, from a set of latent features. Preliminary findings suggest that AFVs can help distinguish among several types of adversarial attacks (e.g., PGD versus Carlini-Wagner) with close to 93% accuracy on the CIFAR-10 dataset. The results open the door to using AFV-based methods for exploring not only adversarial attack detection but also classification of the attack type and then design of attack-specific mitigation strategies.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

18 of 23 references.

References · 18

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2016Wide Residual Networkscited by 3,057
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  9. 2017Detecting Adversarial Samples from Artifactscited by 244
  10. 2017On Detecting Adversarial Perturbationscited by 232
  11. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  12. 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
6 more
  1. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  2. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  3. 2017Adversarial and Clean Data Are Not Twinscited by 52
  4. 2016Early Methods for Detecting Adversarial Imagescited by 36
  5. 2019Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspectioncited by 16
  6. 2019Detecting Adversarial Examples through Nonlinear Dimensionality Reductioncited by 3

Built on by

Not cited yet.