Metraipolis › archive › dc_714e0940430e

WebMaze: Defending Against LLM-Powered Web Scanners with Functionality-Coupled Deception — arXiv:2610.38524

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38524
License (as archived)
CC0-1.0
Archived
2026-11-01T02:21:10.180Z
SHA-256 of the archived text
62a0343418644ac02d0d74d7a9caca3130d6e330cb76c773f66eea5a1e13ca5f
Stable URL of this page
https://metraipolis.com/documento/dc_714e0940430e

How to cite

WebMaze: Defending Against LLM-Powered Web Scanners with Functionality-Coupled Deception — arXiv:2610.38524 — arXiv (en), https://arxiv.org/abs/2610.38524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_714e0940430e (Metraipolis archive dc_714e0940430e, sha256 62a0343418644ac02d0d74d7a9caca3130d6e330cb76c773f66eea5a1e13ca5f)
BibTeX
@misc{dc714e0940430e,
  title = {WebMaze: Defending Against LLM-Powered Web Scanners with Functionality-Coupled Deception — arXiv:2610.38524},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38524},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_714e0940430e; sha256 62a0343418644ac02d0d74d7a9caca3130d6e330cb76c773f66eea5a1e13ca5f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 worlds from the application's existing views. The traps blend into genuine components and expose entry points to decoy worlds that sustain exploration through connected pages and interactions without changing genuine functionality. Across 12 web applications and three LLM-based scanners under the default no-disclosure setting, decoy pages account for an average of 93.0% of the distinct pages requested per run. This demonstrates that WebMaze effectively diverts scanners away from genuine application pages and into the generated decoy worlds. Even when explicitly informed about the decoy mechanism and instructed to avoid decoy pages, scanners continue to explore predominantly decoy pages.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.38524 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:12:13.368Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).