Metraipolis › archive › dc_3d77e6e1bc84
Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond — arXiv:2609.03999
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03999
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:58:03.509Z
- SHA-256 of the archived text
8782da8537478f86612342c48b14be7c206eb703cdbcabc381e3adf610f2cf10- Stable URL of this page
https://metraipolis.com/documento/dc_3d77e6e1bc84
How to cite
Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond — arXiv:2609.03999 — arXiv (en), https://arxiv.org/abs/2609.03999 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d77e6e1bc84 (Metraipolis archive dc_3d77e6e1bc84, sha256 8782da8537478f86612342c48b14be7c206eb703cdbcabc381e3adf610f2cf10)
BibTeX
@misc{dc3d77e6e1bc84,
title = {Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond — arXiv:2609.03999},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03999},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d77e6e1bc84; sha256 8782da8537478f86612342c48b14be7c206eb703cdbcabc381e3adf610f2cf10},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03999. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are becoming integral to web applications and browser agents, transforming online interactions while introducing new attack vectors and reshaping longstanding web vulnerabilities. Classical threats such as cross-site scripting (XSS) can be amplified through LLM-mediated interactions, while LLM-specific vulnerabilities can propagate across web applications, introducing attacks such as prompt injection. Securing modern web systems therefore requires understanding interactions between traditional and LLM-specific threats across the system lifecycle. Unlike prior surveys treating web and LLM security separately, this survey provides a unified analysis of how LLMs amplify web vulnerabilities across client-side, server-side, and pipeline layers while evaluating defenses and their limitations. The analysis examines extending NIST and ISO/IEC AI security frameworks to the security needs of LLM-enabled web environments. Three unresolved challenges are identified: adversarial natural-language instructions, autonomous agent security, and post-deployment security through continuous monitoring and adaptation. An LLM-aware monitoring and control framework is proposed, integrating semantic input validation, prompt integrity protection, output isolation, agent governance, and runtime monitoring. This unified perspective characterizes the evolving threat landscape and outlines future directions for secure AI-enabled web systems. Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CY). Categorie arXiv: Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.03999 — 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 2026-10-17T01:12:46.511Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).