An LSTM based cross-site scripting attack detection scheme for Cloud Computing environments

Abstract

Abstract Cloud Computing plays a pivotal role in facilitating the Internet of Things (IoT) and its diverse applications. Users frequently access and store data on remote servers in Cloud Computing environments through web browsers. Consequently, attackers may exploit vulnerabilities in web browsing to embed malicious code into web pages, enabling them to launch attacks on remote servers in Cloud Computing environments. Due to its complexity, prevalence, and significant impact, XSS has consistently been recognized as one of the top ten web security vulnerabilities by OWASP. The existing XSS detection technology requires optimization: manual feature extraction is time-consuming and heavily reliant on domain knowledge, while the current confusion technology and complex code logic contribute to a decline in the identification of XSS attacks. This paper proposes a character-level bidirectional long-term and short-term memory network model based on a multi-attention mechanism. The bidirectional long-term and short-term memory network ensures the association of current features with preceding and subsequent text, while the multi-attention mechanism extracts additional features from different feature subspaces to enhance the understanding of text semantics. Experimental results demonstrate the effectiveness of the proposed model for XSS detection, with an F1 score of 98.71%.

Keywords

• Network security
• XSS detection
• Bidirectional long-term and short-term memory network
• Multi-head Attention mechanism