mlsanityData to 14 Oct 2026

A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison

arXiv 2510.02707 ↗First posted 3 Oct 2025cs.CR cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this work, we propose a statistical approach that establishes a detection baseline before a neural network's deployment, enabling effective real-time adversarial detection. We generate a metric of adversarial presence by comparing the behavior of a compressed/uncompressed neural network pair. Our method has been tested against state-of-the-art techniques, and it achieves near-perfect detection across a wide range of attack types. Moreover, it significantly reduces false positives, making it both reliable and practical for real-world applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 19 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

15 of 19 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  8. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  9. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  10. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  11. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  12. 2018The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examplescited by 12
3 more
  1. 2019Attack Agnostic Statistical Method for Adversarial Detectioncited by 2
  2. 2020Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysiscited by 2
  3. 2022Attack-Agnostic Adversarial Detectioncited by 1

Built on by

Not cited yet.