Topological Safeguard for Evasion Attack based on the Interpretability of Artificial Neural Network Behavior
Preprint
Abstract
In the last years, Deep Learning technology has been proposed in different fields, bringing many advances in each of them, but identifying new threats in these solutions regarding cybersecurity. Those implemented models have brought several vulnerabilities associated with Deep Learning technology. Moreover, those allow taking advantage of the implemented model, obtaining private information, and even modifying the model's decision-making. Therefore, interest in studying those vulnerabilities/attacks and designing defenses to avoid or fight them is gaining prominence among researchers. In particular, the widely known evasion attack is being analyzed by researchers; thus, several defenses to avoid such a threat can be found in the literature. Since the presentation of the L-BFG algorithm, this threat concerns the research community. However, it continues developing new and ingenious countermeasures since there is no perfect defense for all the known evasion algorithms. In this work, a novel detector of evasion attacks is developed. It focuses on the information of the activations of the neurons given by the model when an input sample is injected. Moreover, it puts attention to the topology of the targeted deep learning model to analyze the activations according to which neurons are connecting. This approach has been decided because the literature shows that the targeted model's topology contains essential information about if the evasion attack occurs. For this purpose, a huge data preprocessing is required to introduce all this information in the detector, which uses the Graph Convolutional Neural Network (GCN) technology. Thus, it understands the topology of the target model, obtaining promising results and improving the outcomes presented in the literature related to similar defenses.Keywords
All Related Versions
- Version 1, 2024-02-12, ArXiv
- Version 2, 2024-02-13, ArXiv
- Published version: Pattern Recognition, 147.
This publication has 14 references indexed in Scilit:
- Improving adversarial robustness by learning shared informationPattern Recognition, 2022
- ImageNet-Patch: A dataset for benchmarking machine learning robustness against adversarial patchesPattern Recognition, 2022
- Adversarial example detection for DNN models: a review and experimental comparisonArtificial Intelligence Review, 2022
- Sampling Methods for Efficient Training of Graph Convolutional Networks: A SurveyIEEE/CAA Journal of Automatica Sinica, 2021
- Towards Security Threats of Deep Learning Systems: A SurveyIEEE Transactions on Software Engineering, 2020
- Defending network intrusion detection systems against adversarial evasion attacksFuture Generation Computer Systems, 2020
- Poisoning and Evasion Attacks Against Deep Learning Algorithms in Autonomous VehiclesIEEE Transactions on Vehicular Technology, 2020
- Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution SummarizationsIEEE Transactions on Visualization and Computer Graphics, 2019
- Adversarial attacks on medical machine learningScience, 2019
- Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks2014