Study on Adversarial Attacks Techniques, Learning Methods and Countermeasures: Application to Anomaly Detection

Anis Bouaziz, Manh-Dung Nguyen, Valeria Valdés, Ana Cavalli, Ana Cavalli, Wissam Mallouli

2023

Abstract

Adversarial attacks on AI systems are designed to exploit vulnerabilities in the AI algorithms that can be used to manipulate the output of the system, resulting in incorrect or harmful behavior. They can take many forms, including manipulating input data, exploiting weaknesses in the AI model, and poisoning the training samples used to develop the AI model. In this paper, we study different types of adversarial attacks, including evasion, poisoning, and inference attacks, and their impact on AI-based systems from different fields. A particular emphasis is placed on cybersecurity applications, such as Intrusion Detection System (IDS) and anomaly detection. We also depict different learning methods that allow us to understand how adversarial attacks work using eXplainable AI (XAI). In addition, we discuss the current state-of-the-art techniques for detecting and defending against adversarial attacks, including adversarial training, input sanitization, and anomaly detection. Furthermore, we present a comprehensive analysis of the effectiveness of different defense mechanisms against different types of adversarial attacks. Overall, this study provides a comprehensive overview of challenges and opportunities in the field of adversarial machine learning, and serves as a valuable resource for researchers, practitioners, and policymakers working on AI security and robustness. An application for anomaly detection, especially malware detection is presented to illustrate several concepts presented in the paper.

Paper Citation

in Harvard Style

Bouaziz A., Nguyen M., Valdés V., Cavalli A. and Mallouli W. (2023). Study on Adversarial Attacks Techniques, Learning Methods and Countermeasures: Application to Anomaly Detection. In Proceedings of the 18th International Conference on Software Technologies - Volume 1: ICSOFT; ISBN 978-989-758-665-1, SciTePress, pages 510-517. DOI: 10.5220/0012125100003538

in Bibtex Style

@conference{icsoft23,
author={Anis Bouaziz and Manh-Dung Nguyen and Valeria Valdés and Ana Cavalli and Wissam Mallouli},
title={Study on Adversarial Attacks Techniques, Learning Methods and Countermeasures: Application to Anomaly Detection},
booktitle={Proceedings of the 18th International Conference on Software Technologies - Volume 1: ICSOFT},
year={2023},
pages={510-517},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012125100003538},
isbn={978-989-758-665-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Conference on Software Technologies - Volume 1: ICSOFT
TI - Study on Adversarial Attacks Techniques, Learning Methods and Countermeasures: Application to Anomaly Detection
SN - 978-989-758-665-1
AU - Bouaziz A.
AU - Nguyen M.
AU - Valdés V.
AU - Cavalli A.
AU - Mallouli W.
PY - 2023
SP - 510
EP - 517
DO - 10.5220/0012125100003538
PB - SciTePress