Cross-Site Scripting (XSS) attacks remain a significant threat in web security, allowing attackers to inject malicious scripts into trusted websites. Traditional detection methods often struggle with high false-positive and false-negative rates, especially when dealing with obfuscated or complex attack vectors. Recent studies have introduced machine learning (ML) and deep learning techniques to enhance XSS detection capabilities. For instance, a study published in the journal Computers & Security proposed a model that achieved a precision rate of 99.8% and a recall rate of 99.1% for XSS detection by utilizing a two-channel feature fusion embedded in a self-attention mechanism. sciencedirect.com Similarly, research in the Journal of Cloud Computing introduced a character-level bidirectional long-term and short-term memory network model based on a multi-attention mechanism, demonstrating an F1 score of 98.71% in XSS detection. journalofcloudcomputing.springeropen.com
These advancements highlight the potential of AI-driven approaches in improving the accuracy and efficiency of XSS detection systems. By leveraging sophisticated algorithms, these models can better identify and mitigate XSS attacks, even those employing complex obfuscation techniques. The integration of AI into web security practices represents a promising direction for enhancing the resilience of web applications against evolving cyber threats.