Two systems based on Principal Component Analysis (PCA) have been proposed for spotting adversarial samples: Standard Principal Component Analysis (SPCA) and Outlier Filtered Principal Component Analysis (OFPCA).
Abstract
Cybersecurity frameworks are increasingly incorporating machine learning-based Intrusion Detection Systems (IDS) into their security measures. Despite the effectiveness of these systems, they remain susceptible to different forms of attacks that take advantage of their operation; specifically, those that are designed to circumvent their protective mechanisms. For example, modifications made to network traffic can produce “adversarial samples,” which are designed to go undetected. To tackle this issue, two systems based on Principal Component Analysis (PCA) have been proposed for spotting adversarial samples: Standard Principal Component Analysis (SPCA) and Outlier Filtered Principal Component Analysis (OFPCA). SPCA identifies the basic structure of normal network traffic through principal components and detects adversarial attacks by looking at reconstruction errors. A sample is projected onto the principal components and then reconstructed in the original space. The difference between the original and reconstructed features is the reconstruction error. Larger errors can indicate manipulation. OFPCA, on the other hand, is trained only on normal samples after removing outlier data points from the training set. When testing SPCA method using the NSL-KDD dataset, it achieved an AUC-ROC score of 0.97 in detecting FGSM adversarial samples. OFPCA had a higher AUC-ROC score of 0.99 in identifying FGSM adversarial samples. OFPCA performed better than SPCA and other techniques, when tested under different adversarial attacks.
An extensive literature review on the adversarial attack methods, detection and defence techniques of critical network infrastructures and suggests the creation of multi-strategic, adaptive, and real-time adversarial threat management systems that can sustain themselves in a heterogeneous network environment.
F. Okoye, Aghaizu Herman Chijioke, Shamsudeen Mohammed S.B· International journal of re...· 0 citations
A detailed empirical assessment of targeted adversarial vulnerability and defensive behaviour in a multi-class NIDS setting is presented and the results highlight long-standing, class-specific, robustness gaps and provide insights that could be used to design more robust intrusion detection systems.
Khushnaseeb Roshan, Faraz Masood, A. Zafar et al.· Discover Computing· 1 citation
A Kitchenham-informed systematic literature review methodology, this review synthesizes 186 studies published between 2018 and 2026 and develops a perturbation-realism taxonomy, ranging from feature-level manipulation to executable packet-level attacks, that clarifies when reported success corresponds to deployable risk.
: Machine learning has radically transformed network security, enabling intrusion detection systems capable of identifying malicious traffic with near-perfect accuracy on standard benchmarks. However, these systems remain critically vulnerable to adversarial examples—subtly manipulated inputs designed to escape detection—where performance can severely drop under minimal perturbation. This paper introduces the Hierarchical Adversarially-Driven Escalation System (hades), a framework that addresses this vulnerability through three coordinated mechanisms. First, dedicated detectors are trained for each network protocol, enabling each model to specialize in specific traffic patterns it will face in practice. Second, these detectors are continuously hardened by simulating an arms race between an attacking agent, which learns to find the most damaging evasion strategies, and a defending model that adapts in response, thus producing classifiers that remain robust across a wide range of attack types. Third, incoming traffic is routed through a cost-aware pipeline that reserves expensive analysis for uncertain or suspicious flows, keeping average processing time at 5.4 ms per batch on normal traffic. hades is evaluated on CIC-IDS-2018, a large-scale real-world network dataset, and maintains near-perfect detection accuracy under both normal and adversarial conditions, with robustness verified across nine distinct attack strategies and 95% bootstrap confidence intervals of maximum width 0.0007.
A. Derhab, Adlen Kerboua, N. Seddari et al.· Computer Modeling in Enginee...· 0 citations
The review explores the key adversarial attack classes: poisoning, evasion, model extraction, model extraction, model inversion, and membership inference and also white-box, black-box, and grey-box threat models.
Ujjwal Deshmukh· International Journal of Inn...· 0 citations
A thorough analysis of a modest version of a suggested system that use Support Vector Machines (SVM) to address networking anomaly and misuse detection in the face of insurmountable obstacles, foreseeing an all-encompassing solution to modern network security issues.
Gaurav Kishor Saxena, Shambhu Dayal Sahu· International Journal of Cre...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
