Cybersecurity attacks pose a significant threat to the security of network systems through intrusions and illegal communications. Measuring the vulnerability of cybersecurity is crucial for refining the overall system security to further mitigate potential security risks. Machine learning (ML)-based intrusion detection systems (IDSs) are mainly designed to detect malicious network traffic. Unfortunately, ML models have recently been demonstrated to be vulnerable to adversarial perturbation, and therefore enable potential attackers to crash the system during normal operation. Among different attacks, generative adversarial networks (GANs) have been known as one of the most powerful threats to cybersecurity systems. To address these concerns, it is important to explore new defense methods and understand the nature of different types of attacks. In this paper, we investigate four serious attacks, GAN, Zeroth-Order Optimization (ZOO), kernel density estimation (KDE), and DeepFool attacks, on cybersecurity. Deep analysis was conducted on these attacks using three different cybersecurity datasets, ADFA-LD, CSE-CICIDS2018, and CSE-CICIDS2019. Our results have shown that KDE and DeepFool attacks are stronger than GANs in terms of attack success rate and impact on system performance. To demonstrate the effectiveness of our approach, we develop a defensive model using adversarial training where the DeepFool method is used to generate adversarial examples. The model is evaluated against GAN, ZOO, KDE, and DeepFool attacks to assess the level of system protection against adversarial perturbations. The experiment was conducted by leveraging a deep learning model as a classifier with the three aforementioned datasets. The results indicate that the proposed defensive model refines the resilience of the system and mitigates the presented serious attacks.
Machine learning (ML) techniques have significantly enhanced decision support systems to render them more accurate, efficient, and faster. ML classifiers in securing networks, on the other hand, face a disproportionate risk from the sophisticated adversarial attacks compared to other areas, such as spam filtering, intrusion, and virus detection, and this introduces a continuous competition between malicious users and preventers. Attackers test ML models with inputs that have been specifically crafted to evade these models and obtain inaccurate forecasts. This paper presents a comprehensive review of attack and defensive techniques in ML-based NIDSs. It highlights the current serious challenges that the systems face in preserving robustness against adversarial attacks. Based on our analysis, with respect to their current superior performance and robustness, ML-based NIDS require urgent attention to develop more robust techniques to withstand such attacks. Finally, we discuss the current existing approaches in generating adversarial attacks and reveal the limitations of current defensive approaches. In this paper, the most recent advancements, such as hybrid defensive techniques that integrate multiple strategies to prevent adversarial attacks in NIDS, have highlighted the ongoing challenges.
5 February 2025 in Al-Salam Journal for Engineering and Technology
Network Intrusion Detection Systems (NIDS) have played an important role in protecting computer networks against illegal or unauthorized access and many cyberattacks. Given the advancement of machine learning (ML) approaches, NIDS have become more effective in detecting various complex anomalies in computer networks. However, the increasing complexity in adversarial attacks (AAs) poses a significant challenge to such systems. Cyberattacks are estimated to cost approximately $10.5 trillion annually by 2025, and this encourages researchers to improve and develop ML-based NIDS in order to address adversarial vulnerabilities in these systems to remain the systems resilient to modern attacks. In this review, we reveal the weaknesses of ML-based IDS to AAs in which many different attack techniques, such as evasion, poisoning, and generative adversarial networks (GAN) have been included. Also, this study presents and evaluates current possible defensive approaches against AAs, including but not limited to anomaly detection approaches, adversarial training, and feature selection. We also provide a comparative analysis of different ML models used in NIDS in order to further evaluate the system’s susceptibility to sophisticated AAs. A discussion on future work to improve ML-based NIDS resilience against sophisticated attacks is also given.
Machine learning (ML) techniques have significantly enhanced decision support systems to render the systems more accurate, efficient, and faster. ML classifiers in securing networks, on the other hand, face a disproportionate risk of mettle adversarial attacks as compared to other areas, including spam filtering and intrusion, and virus detections, and this introduces a continuous competition between malicious users and preventers. Attackers test ML models with inputs that have been specifically produced for evading these models and provide an inaccurate forecast. This paper presents a comprehensive review of attack and defensive techniques in ML-based NIDSs. It highlights the current serious challenges that the systems face in preserving robustness against adversarial attacks. Based on our analysis, with respect to their current superior performance and robustness, ML-based NIDS require rapid attention to develop more robust techniques to withstand such attacks. Finally, we discuss the current existing approaches in generating adversarial attacks and reveal the limitations of current defensive approaches. In this paper, the most recent advancements, such as hybrid defensive techniques that integrate multiple approaches to prevent adversarial attacks in NIDS, have effectively highlighted the ongoing challenges.