LATIDIA · Ciberseguridad

WebMaze: Defensa contra escáneres web basados ​​en LLM mediante engaño acoplado a la funcionalidad

arXiv:2610.38524v1 Anuncio Tipo: nuevo Resumen: Los modelos de lenguaje grandes (LLM) han permitido un escaneo de vulnerabilidades más efectivo de las aplicaciones web. Sin embargo, estas capacidades también hacen que sea significativamente más fácil para los ataques

La noticia

arXiv:2610.38524v1 Announce Type: new Abstract: Large language models (LLMs) have enabled more effective vulnerability scanning of web applications. However, these capabilities also make it significantly easier for attackers to automate cyberattacks on the web. In this work, we investigate how to divert malicious LLM-based web scanning, with preservation of genuine functionality as a deployment requirement. We systematically study six LLM-based scanners and summarize how they gather information and iteratively select actions based on observations. Guided by the study, we then present WebMaze, a defense that preserves genuine application functionality while diverting LLM-based scanners to a generated decoy world. WebMaze embeds functionality-coupled traps in genuine pages and constructs view-tailored interactive decoy