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.
Abstract
Ensuring the robustness of Network Intrusion Detection Systems (NIDS) against adversarial manipulation is an increasingly important problem in the field of computer network security today. Recent breakthroughs in adversarial machine learning have brought to light the vulnerability of NIDS that rely on deep learning models to carefully crafted perturbations, which could significantly degrade the detection and classification performance. In the present investigation, we carry out a systematic empirical investigation of targeted white box adversarial attacks upon a deep learning based multi-class NIDS. A DNN-based intrusion detection model is first evaluated in benign operational condition and then, is subjected to targeted adversarial perturbations introduced using the Fast Gradient Sign Method. To address the observed vulnerabilities, we follow Adversarial Training as a heuristic defence mechanism. All the experiments made use of a subset of the Canadian Institutes of Cybersecurity Intrusion Detection System benchmark data. The proposed NIDS achieves an accuracy of 97.11% in pre-attack conditions. When the model is fed with targeted adversarial perturbations, the classification accuracy decreases to a large degree to 33.27%, 52.15%, 37.89%, and 29.45% when the Benign, DDoS, DoS-Hulk, and PortScan classes are taken as the target, respectively. Incorporating Adversarial Training improves the robustness and increases the accuracy to 73.83%, 76.82%, 75.71% and 71.96% in respective targeted scenarios, although the recovery still depends on the class. Rather than present new attack or defence, this study presents a detailed empirical assessment of targeted adversarial vulnerability and defensive behaviour in a multi-class NIDS setting. The results highlight long-standing, class-specific, robustness gaps and provide insights that could be used to design more robust intrusion detection systems.
Many of the critical networks are now vulnerable to complex security threats, especially those launched by adversaries against the machine learning-driven security systems used by these networks. Such attacks take advantage of weaknesses in AI systems by perturbing the model with carefully designed perturbations, which result in misclassification of malicious content as benign, compromising the system's confidentiality, integrity, and availability. The adversarial threat is unlike traditional cyberattacks; it is dynamic, adaptive and can circumvent traditional intrusion detection capabilities. This paper provides an extensive literature review on the adversarial attack methods, detection and defence techniques of critical network infrastructures. This review includes peer-reviewed publications published between 2019 and 2024 from the leading academic databases such as IEEE Xplore, SpringerLink, ScienceDirect and Google Scholar. The total number of studies analyzed were 48, covering contributions in the fields of creating adversarial attack methods, machine learning and deep learning based detection methods, and mitigation techniques. The results indicate that adversarial attacks can be divided into the following categories: evasion attacks, poisoning attacks, and exploratory attacks, where some of the more sophisticated methods, including those based on gradient, optimization, and reinforcement learning, are very effective in evading security systems. Current solutions, however, suffer from limited real-time adaptability, cross-domain generalization ability, explainability and integration across the attack lifecycle. While there are several defence mechanisms proposed, such as adversarial training, anomaly detection, and input transformation, existing defences have difficulties in being adaptable in real time, cross-domain generalizable, explainable and suitable for certain phases of the attack lifecycle. The study highlights a number of critical research challenges such as the lack of a common defence framework, inadequate real-time detection capabilities, absence of a standardized data sets and poor ability to withstand adaptive adversaries. The paper 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
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
It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System (NIDS). However, NIDS faces a major security concern due to its susceptibility to adversarial attacks. Adversarial attacks aim to deceive NIDS by crafting and injecting adversarial examples into the system. These adversarial inputs can deceive the NIDS into misclassifying benign network traffic as malicious. We developed a resilient hybrid defense mechanism aimed to mitigate the impact of two potent adversarial attacks: Fast Gradient Sign Method (FGSM) and Carlini&Wagner (C&W) attack. Our hybrid defense approach leverages the combined strength of two heuristic defense methods: Adversarial Training (AT) and Gaussian Data Augmentation (GDA). GDA provides multi-directional defense, while AT enhances NIDS robustness against specific adversarial vectors. Under pre-attack scenarios, NIDS demonstrated good accuracy and f1-score. However, in the post-attack scenario, its accuracy significantly dropped under FGSM and C&W attacks (0.2649 and 0.4961, respectively). Our proposed hybrid defense method effectively mitigated these adversarial threats, with post-defense accuracy of 96.57% and 89.20% for FGSM and C&W attacks. We evaluated the defense strategy across a range of epsilon and confidence noise factor values (ranging from 0.0001 to 0.0009). This research provides a good direction for future researchers in the emerging area of adversarial machine learning from a security perspective.
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.
N. Dhinakaran, S. Anto· Frontiers of Computer Scienc...· 0 citations
Experimental results indicate that CNN-based NIDS are more vulnerable to adversarial attacks than ANN-based models, with adversarial examples successfully transferring across architectures, highlighting the critical risks associated with adversarial transferability.
Aasim Zafar, Shazra Wali, Sheikh Burhan Ul Haque· International Journal of Inf...· 0 citations
A detailed overview of the security risks associated with adversarial attacks is offered, including evasion attacks carried out at inference time, data poisoning that corrupts the training process, backdoor insertion that hides dormant triggers inside a model, and model inversion that leaks private information back out of a trained system.
Harsh Verma· International Journal of Sci...· 0 citations