A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks
Abstract AI techniques for cybersecurity are advancing, but AI-based classifiers are suspectable of adversarial attacks. It is challenging to quantify the efforts required of an adversary to manipulate a system and quantify this resilience such that different systems can be compared using standard m...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-024-00686-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544321083375616 |
|---|---|
| author | Kousik Barik Sanjay Misra Luis Fernandez-Sanz |
| author_facet | Kousik Barik Sanjay Misra Luis Fernandez-Sanz |
| author_sort | Kousik Barik |
| collection | DOAJ |
| description | Abstract AI techniques for cybersecurity are advancing, but AI-based classifiers are suspectable of adversarial attacks. It is challenging to quantify the efforts required of an adversary to manipulate a system and quantify this resilience such that different systems can be compared using standard metrics. The study intends to quantify the actions required when an attacker abuses an AI-based system and propose a model to assess the attacker’s cybersecurity resilience. The study proposes an Egyptian Vulture Optimized Adaptive Elman Recurrent Neural Networks (EVO-AERNN) model to assess cybersecurity resilience and compare it with machine learning and deep learning-based classifiers. It illustrates the potential of using adversary-aware feature sampling to build more robust classifiers and use an optimized algorithm to maintain inherent resilience. The proposed model is achieved with an accuracy of 0.995, an F1 score of 0.9932, a precision of 0.9921, a recall (before an attack) of 0.987, a recall (after an attack) of 0.632, and a severity score of 0.363. The proposed model is further validated with a secondary dataset. This study paves the way for a more comprehensive knowledge of adversarial attack scenarios on network systems and offers valuable insights, inspiring further research on advancing cybersecurity studies. |
| format | Article |
| id | doaj-art-da50e569d2d644099ed0d19f40bfdcc5 |
| institution | Kabale University |
| issn | 1875-6883 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj-art-da50e569d2d644099ed0d19f40bfdcc52025-01-12T12:38:45ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832024-11-0117113210.1007/s44196-024-00686-3A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber AttacksKousik Barik0Sanjay Misra1Luis Fernandez-Sanz2Department of Computer Science, Universidad de AlcaláDepartment of Computer Science and Communication, Østfold University CollegeDepartment of Computer Science, Universidad de AlcaláAbstract AI techniques for cybersecurity are advancing, but AI-based classifiers are suspectable of adversarial attacks. It is challenging to quantify the efforts required of an adversary to manipulate a system and quantify this resilience such that different systems can be compared using standard metrics. The study intends to quantify the actions required when an attacker abuses an AI-based system and propose a model to assess the attacker’s cybersecurity resilience. The study proposes an Egyptian Vulture Optimized Adaptive Elman Recurrent Neural Networks (EVO-AERNN) model to assess cybersecurity resilience and compare it with machine learning and deep learning-based classifiers. It illustrates the potential of using adversary-aware feature sampling to build more robust classifiers and use an optimized algorithm to maintain inherent resilience. The proposed model is achieved with an accuracy of 0.995, an F1 score of 0.9932, a precision of 0.9921, a recall (before an attack) of 0.987, a recall (after an attack) of 0.632, and a severity score of 0.363. The proposed model is further validated with a secondary dataset. This study paves the way for a more comprehensive knowledge of adversarial attack scenarios on network systems and offers valuable insights, inspiring further research on advancing cybersecurity studies.https://doi.org/10.1007/s44196-024-00686-3Adversarial learningResilienceAI classifiersCyber security |
| spellingShingle | Kousik Barik Sanjay Misra Luis Fernandez-Sanz A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks International Journal of Computational Intelligence Systems Adversarial learning Resilience AI classifiers Cyber security |
| title | A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks |
| title_full | A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks |
| title_fullStr | A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks |
| title_full_unstemmed | A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks |
| title_short | A Model for Estimating Resiliency of AI-Based Classifiers Defending Against Cyber Attacks |
| title_sort | model for estimating resiliency of ai based classifiers defending against cyber attacks |
| topic | Adversarial learning Resilience AI classifiers Cyber security |
| url | https://doi.org/10.1007/s44196-024-00686-3 |
| work_keys_str_mv | AT kousikbarik amodelforestimatingresiliencyofaibasedclassifiersdefendingagainstcyberattacks AT sanjaymisra amodelforestimatingresiliencyofaibasedclassifiersdefendingagainstcyberattacks AT luisfernandezsanz amodelforestimatingresiliencyofaibasedclassifiersdefendingagainstcyberattacks AT kousikbarik modelforestimatingresiliencyofaibasedclassifiersdefendingagainstcyberattacks AT sanjaymisra modelforestimatingresiliencyofaibasedclassifiersdefendingagainstcyberattacks AT luisfernandezsanz modelforestimatingresiliencyofaibasedclassifiersdefendingagainstcyberattacks |