Re-Evaluating Deep Learning Attacks and Defenses in Cybersecurity Systems
Open Access
- 16 December 2024
- journal article
- research article
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 8 (12) , 191
Abstract
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.Keywords
This publication has 52 references indexed in Scilit:
- Future of generative adversarial networks (GAN) for anomaly detection in network security: A reviewComputers & Security, 2024
- M-MultiSVM: An efficient feature selection assisted network intrusion detection system using machine learningComputers & Security, 2023
- Efficient intrusion detection using multi-player generative adversarial networks (GANs): an ensemble-based deep learning architectureNeural Computing and Applications, 2023
- Generative adversarial networks review in earthquake-related engineering fieldsBulletin of Earthquake Engineering, 2023
- IDSGAN: Generative Adversarial Networks for Attack Generation Against Intrusion Detection2022
- Adversarial vulnerability of deep neural network-based gait event detection: A comparative study using accelerometer-based dataBiomedical Signal Processing and Control, 2022
- PNRank: Unsupervised ranking of person name entities from noisy OCR textDecision Support Systems, 2022
- Fooling intrusion detection systems using adversarially autoencoderDigital Communications and Networks, 2021
- Machine learning methods for cyber security intrusion detection: Datasets and comparative studyComputer Networks, 2021
- Improving DNN Robustness to Adversarial Attacks Using Jacobian Regularization2018