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

2025/10/03 by Wimalasuriya, Chinthana, Tragoudas, Spyros
#Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2510.02707

Abstract

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.

Citations

• Attack-Agnostic Adversarial Detection
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
• Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis
• Square Attack: a query-efficient black-box adversarial attack via random search
• Attack Agnostic Statistical Method for Adversarial Detection
• Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Adversarial Robustness Toolbox v1.0.0
• The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Towards Evaluating the Robustness of Neural Networks
• Deep Residual Learning for Image Recognition
• DeepFool: a simple and accurate method to fool deep neural networks
• Explaining and Harnessing Adversarial Examples
• On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other

Related

• Universal and Efficient Detection of Adversarial Data through Nonuniform Impact on Network Layers
• RAID: Randomized Adversarial-Input Detection for Neural Networks
• TREATED:Towards Universal Defense against Textual Adversarial Attacks
• Attack-Agnostic Adversarial Detection
• Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?