Statically identifying XSS using deep learning

Identifier statiquement des failles XSS à l'aide d'apprentissage en profondeur

Heloise Maurel (1) , Santiago Vidal (2) , Tamara Rezk (1)

1 INDES - Secure Diffuse Programming
2 ISISTAN - Instituto Superior de Ingeniería de Software Tandil [Buenos Aires]

Cross-site Scripting (XSS) is ranked first in the top 25 Most Dangerous Software Weaknesses (2020) of Common Weakness Enumeration (CWE) and places this vulnerability as the most dangerous among programming errors. In this work, we explore static approaches to detect XSS vulnerabilities using neural networks. We compare two different code representations based on Natural Language Processing (NLP) and Programming Language Processing (PLP) and experiment with models based on different neural network architectures for static analysis detection in PHP and Node.js. We train and evaluate the models using synthetic databases. Using the generated PHP and Node.js databases, we compare our results with a well-known static analyzer for PHP code, ProgPilot, and a known scanner for Node.js, AppScan static mode. Our analyzers using neural networks overcome the results of existing tools in all cases

Domaines: Arithmétique des ordinateurs; Cryptographie et sécurité [cs.CR]; Informatique [cs]; Apprentissage [cs.LG]; Base de données [cs.DB]; Web

Heloise Maurel, Santiago Vidal, Tamara Rezk. Statically identifying XSS using deep learning. Science of Computer Programming, 2022, 219, pp.102810. ⟨10.1016/j.scico.2022.102810⟩. ⟨hal-03684437⟩