Assessment of existing cyber-attack detection models for web-based systems

Abstract

In the current technological environment, different entities engage in intricate cyber security approaches in order to counter damages and disruptions in web-based systems. The design of the security protocols relies on the guarantee that attacks are prevented in the web-based systems. Prevention and detection using techniques such as access control tools, encryption and firewalls present limitations in the full protection of web-based systems. Furthermore, despite the sophistication of current systems, there are still shortfalls in high false positive and false negative threat detection rates, which is attributed to poor adaptation by systems and networks to the changing threats and behavior of cyber-criminals. In this perspective, this survey paper discusses the existing cyber-attack detection models, and recommends the cyber-attack detection models and techniques that are appropriate for web-based systems. It is evident that deep learning techniques offer better performance and robustness compared to traditional machine learning techniques and other non-artificial intelligence-based techniques. Deep learning techniques learn and extract features automatically without human intervention and can also handle big and multidimensional data more conventionally than the other techniques.

ML and DL-based Phishing Website Detection: The Effects of Varied Size Datasets and Informative Feature Selection Techniques

“…Adam optimizer combines the functions of two different optimization techniques namely SGD and RMSprop and outperforms the SGD and RMSprop optimization techniques in terms of accuracy as per [31]. minimal false alarm rates, and affordable computation costs [3]. In this study, results in bold italics were improved performance indicators, those in bold were similar performance indicators, and those in italics were poor performance indicators.…”

“…The phishing website attack success may result in losses in finances, productivity, reputability, credibility, continuity, and damage to national security [2]. Therefore, the development of cyberattack detection systems is essential for the security of sensitive and personal data, data exchanges, and online transactions [3].…”

“…A recent study [3] stated that most cyberattack detection and prevention techniques employed in current systems are incapable of dealing the complexity and dynamic nature of cyberattacks. To address these concerns, it is vital to employ adaptive AI-based techniques like machine learning (ML) and deep learning (DL) by considering enhanced detection, low false alarms, and reasonable costs of computation [3]. As per [7], DL is a subset of ML techniques based on multilayered neural networks.…”

Next Generation AI-Based Firewalls: A Comparative Study

“…In an era marked by the rapid digitization of information and communication, the omnipresence of cyber threats necessitates an evolution in cybersecurity strategies. Traditional firewalls, once the stalwarts of network defense, are grappling with the intricacies of contemporary threats, prompting the emergence of next-generation firewalls (NGFWs) [5]. At the forefront of this technological evolution is the integration of artificial intelligence (AI), offering a paradigm shift in threat detection, prevention, and response.…”

“…NGFWs, by incorporating AI technologies, present a potent solution to address the dynamic and evolving nature of modern cyberattacks. AI's ability to adapt, learn, and analyze patterns in real-time provides a robust defense mechanism against a diverse array of threats, ranging from malware and phishing attacks to advanced persistent threats (APTs) [5]. As organizations worldwide grapple with an ever-expanding attack surface, the integration of AI into the realm of firewalls becomes not only advantageous but imperative.…”