Mitigating Label Flipping Attacks in Malicious URL Detectors Using Ensemble Trees

Malicious URLs provide adversarial opportunities across various industries, including transportation, healthcare, energy, and banking which could be detrimental to business operations. Consequently, the detection of these URLs is of crucial importance; however, current Machine Learning (ML) models are susceptible to backdoor attacks. These attacks involve manipulating a small percentage of training data labels, such as Label Flipping (LF), which changes benign labels to malicious ones and vice versa. This manipulation results in misclassification and leads to incorrect model behavior. Therefore, integrating defense mechanisms into the architecture of ML models becomes an imperative consideration to fortify against potential attacks. The focus of this study is on backdoor attacks in the context of URL detection using ensemble trees. By illuminating the motivations behind such attacks, highlighting the roles of attackers, and emphasizing the critical importance of effective defense strategies, this paper contributes to the ongoing efforts to fortify ML models against adversarial threats within the ML domain in network security. We propose an innovative alarm system that detects the presence of poisoned labels and a defense mechanism designed to uncover the original class labels with the aim of mitigating backdoor attacks on ensemble tree classifiers. We conducted a case study using the Alexa and Phishing Site URL datasets and showed that LF attacks can be addressed using our proposed defense mechanism. Our experimental results prove that the LF attack achieved an Attack Success Rate (ASR) between 50-65% within 2-5%, and the innovative defense method successfully detected poisoned labels with an accuracy of up to 100%.

Unscrambling the Rectification of Adversarial Attacks Transferability across Computer Networks

Convolutional neural networks (CNNs) models play a vital role in achieving state-of-the-art performances in various technological fields. CNNs are not limited to Natural Language Processing (NLP) or Computer Vision (CV) but also have substantial applications in other technological domains, particularly in cybersecurity. The reliability of CNN's models can be compromised because of their susceptibility to adversarial attacks, which can be generated effortlessly, easily applied, and transferred in real-world scenarios. In this paper, we present a novel and comprehensive method to improve the strength of attacks and assess the transferability of adversarial examples in CNNs when such strength changes, as well as whether the transferability property issue exists in computer network applications. In the context of our study, we initially examined six distinct modes of attack: the Carlini and Wagner (C&W), Fast Gradient Sign Method (FGSM), Iterative Fast Gradient Sign Method (I-FGSM), Jacobian-based Saliency Map (JSMA), Limited-memory Broyden fletcher Goldfarb Shanno (L-BFGS), and Projected Gradient Descent (PGD) attack. We applied these attack techniques on two popular datasets: the CIC and UNSW datasets. The outcomes of our experiment demonstrate that an improvement in transferability occurs in the targeted scenarios for FGSM, JSMA, LBFGS, and other attacks. Our findings further indicate that the threats to security posed by adversarial examples, even in computer network applications, necessitate the development of novel defense mechanisms to enhance the security of DL-based techniques.