The growing dependence of modern organizations on web applications has led to a significant increase in the number of cyberattacks aimed at disrupting their functionality, compromising data, or gaining unauthorized access to resources. Attackers actively exploit vulnerabilities in web applications to steal confidential information, manipulate databases, and undermine the integrity of services. In response to these threats, Web Application Firewalls (WAF) have become essential security elements, serving to filter and control traffic between web applications and the Internet. Traditional WAFs, which rely on signature-based detection, are effective against known threats but struggle to identify new types of network attacks, particularly zero-day attacks. To overcome these limitations, anomaly-based detection methods have emerged, allowing for the assessment of deviations in request behavior from the norm. Currently, WAFs that combine signature and anomaly detection methods are widely implemented, utilizing machine learning algorithms to adapt to new threats. Furthermore, WAFs incorporate Data Loss Prevention (DLP) methods to protect confidential information. To evaluate the effectiven
📖 افتح في inklap 🔗 DOI 📮 اطلب بحثاً