Radial Basis Function Network: Its Robustness and Ability to Mitigate Adversarial Examples

Chenou, Jules; Hsieh, George; Fields, Tonya

doi:10.1109/csci49370.2019.00024

Cited by 9 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other promising research shows that radial basis function neural networks (RBFNN) are more robust to adversarial examples [119]. RBFNNs fit a non-linear curve during training, as opposed to fitting linear decision boundaries.…”

Section: Adversarial Examples and Model Typementioning

confidence: 99%

Functionality-Preserving Adversarial Machine Learning for Robust Classification in Cybersecurity and Intrusion Detection Domains: A Survey

McCarthy

Ghadafi

Andriotis

et al. 2022

JCP

View full text Add to dashboard Cite

Machine learning has become widely adopted as a strategy for dealing with a variety of cybersecurity issues, ranging from insider threat detection to intrusion and malware detection. However, by their very nature, machine learning systems can introduce vulnerabilities to a security defence whereby a learnt model is unaware of so-called adversarial examples that may intentionally result in mis-classification and therefore bypass a system. Adversarial machine learning has been a research topic for over a decade and is now an accepted but open problem. Much of the early research on adversarial examples has addressed issues related to computer vision, yet as machine learning continues to be adopted in other domains, then likewise it is important to assess the potential vulnerabilities that may occur. A key part of transferring to new domains relates to functionality-preservation, such that any crafted attack can still execute the original intended functionality when inspected by a human and/or a machine. In this literature survey, our main objective is to address the domain of adversarial machine learning attacks and examine the robustness of machine learning models in the cybersecurity and intrusion detection domains. We identify the key trends in current work observed in the literature, and explore how these relate to the research challenges that remain open for future works. Inclusion criteria were: articles related to functionality-preservation in adversarial machine learning for cybersecurity or intrusion detection with insight into robust classification. Generally, we excluded works that are not yet peer-reviewed; however, we included some significant papers that make a clear contribution to the domain. There is a risk of subjective bias in the selection of non-peer reviewed articles; however, this was mitigated by co-author review. We selected the following databases with a sizeable computer science element to search and retrieve literature: IEEE Xplore, ACM Digital Library, ScienceDirect, Scopus, SpringerLink, and Google Scholar. The literature search was conducted up to January 2022. We have striven to ensure a comprehensive coverage of the domain to the best of our knowledge. We have performed systematic searches of the literature, noting our search terms and results, and following up on all materials that appear relevant and fit within the topic domains of this review. This research was funded by the Partnership PhD scheme at the University of the West of England in collaboration with Techmodal Ltd.

show abstract

Section: Adversarial Examples and Model Typementioning

confidence: 99%

Functionality-Preserving Adversarial Machine Learning for Robust Classification in Cybersecurity and Intrusion Detection Domains: A Survey

McCarthy

Ghadafi

Andriotis

et al. 2022

JCP

View full text Add to dashboard Cite

show abstract

“…Other promising research shows that radial basis function neural networks (RBFNN) are more robust to adversarial examples [115]. RBFNNs fit a non-linear curve during training, as opposed to fitting linear decision boundaries.…”

Section: Adversarial Examples and Model Typementioning

confidence: 99%

Functionality-preserving Adversarial Machine Learning For Robust Classification In Cybersecurity And Intrusion Detection Domains: A Survey

McCarthy¹,

Ghadafi²,

Andriotis³

et al. 2022

Preprint

View full text Add to dashboard Cite

Machine learning has become widely adopted as a strategy for dealing with a variety of cybersecurity issues, ranging from insider threat detection to intrusion and malware detection. However, by their very nature, machine learning systems can introduce vulnerabilities to a security defence whereby a learnt model is unaware of so-called adversarial examples that may intentionally result in mis-classification and therefore bypass a system. Adversarial machine learning has been a research topic for over a decade and is now an accepted but open problem. Much of the early research on adversarial examples has addressed issues related to computer vision, yet as machine learning continues to be adopted in other domains, then likewise it is important to assess the potential vulnerabilities that may occur. A key part of transferring to new domains relates to functionality-preservation, such that any crafted attack can still execute the original intended functionality when inspected by a human and/or a machine. In this literature survey, our main objective is to address the domain of adversarial machine learning attacks and examine the robustness of machine learning models in the cybersecurity and intrusion detection domains. We identify the key trends in current work observed in the literature, and explore how these relate to the research challenges that remain open for future works. Inclusion criteria were: articles related to functionality-preservation in adversarial machine learning for cybersecurity or intrusion detection with insight into robust classification. Generally, we excluded works that are not yet peer-reviewed; however, the authors include some significant papers that make a clear contribution to the domain. There is a risk of subjective bias in the selection of non-peer reviewed articles; however, this is mitigated by co-author review. We selected the following databases with a sizeable computer science element to search and retrieve literature: IEEE Xplore, ACM Digital Library, ScienceDirect, Scopus, SpringerLink,Google Scholar. The literature search was conducted upto January 2022. We have striven to ensure a comprehensive coverage of the domain to the best of our knowledge. We have performed systematic searches of the literature, noting our search terms and results, and following up on all materials that appear relevant and fit within the topic domains of this review. This research was funded by the Partnership PhD scheme at the University of the West of England in collaboration with Techmodal Ltd.

show abstract

“…The output of the network is a linear combination of radial basis functions of the inputs and neuron parameters. Despite their architectural simplicity, they have been shown to possess structural resistance to adversarial attacks [13,32,33,34], thanks to their localized nature, thus they are a natural candidate for building fast and secure detectors. The use of RBF activation functions enforces the classifier to assume a desirable compact abating probability property for open set recognition [35,36].…”

Section: Fast Adversarial Example Rejectionmentioning

confidence: 99%

FADER: Fast Adversarial Example Rejection

Crecchi¹,

Melis²,

Sotgiu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time.Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from legitimate training samples at different layer representations -a behavior normally exhibited by adversarial attacks. Despite technical differences, all aforementioned methods share a common backbone structure that we formalize and highlight in this contribution, as it can help in identifying promising research directions and drawbacks of existing methods. The first main contribution of this work is the review of these detection methods in the form of a unifying framework designed to accommodate both existing defenses and newer ones to come. In terms of drawbacks, the overmentioned defenses require comparing input samples against an oversized number of reference prototypes, possibly at different representation layers, dramatically worsening the test-time efficiency. Besides, such defenses are typically based on ensembling classifiers with heuristic methods, rather than optimizing the whole architecture in an end-to-end manner to better perform detection. As a second main contribution of this work, we introduce FADER, a novel technique for speeding up detection-based methods. FADER overcome the issues above by employing RBF networks as detectors: by fixing the number of required prototypes, the runtime complexity of adversarial examples detectors can be controlled. Our experiments outline up to 73× prototypes reduction compared to analyzed detectors for MNIST dataset and up to 50× for CIFAR10 dataset respectively, without sacrificing classification accuracy on both clean and adversarial data.

show abstract

Radial Basis Function Network: Its Robustness and Ability to Mitigate Adversarial Examples

Cited by 9 publications

References 9 publications

Functionality-Preserving Adversarial Machine Learning for Robust Classification in Cybersecurity and Intrusion Detection Domains: A Survey

Functionality-Preserving Adversarial Machine Learning for Robust Classification in Cybersecurity and Intrusion Detection Domains: A Survey

Functionality-preserving Adversarial Machine Learning For Robust Classification In Cybersecurity And Intrusion Detection Domains: A Survey

FADER: Fast Adversarial Example Rejection

Contact Info

Product

Resources

About