Metraipolis › archive › dc_6748eca53d38

AgentShield: Fortifying Web Applications Against AI Agents and Agentic Browsers — arXiv:2610.41181

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41181
License (as archived)
CC0-1.0
Archived
2026-11-02T04:50:25.832Z
SHA-256 of the archived text
526f9b05140cfb2eeb043e7ec880cbb3e00f38a4c472d11d9a366e879dc1ba26
Stable URL of this page
https://metraipolis.com/documento/dc_6748eca53d38

How to cite

AgentShield: Fortifying Web Applications Against AI Agents and Agentic Browsers — arXiv:2610.41181 — arXiv (en), https://arxiv.org/abs/2610.41181 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6748eca53d38 (Metraipolis archive dc_6748eca53d38, sha256 526f9b05140cfb2eeb043e7ec880cbb3e00f38a4c472d11d9a366e879dc1ba26)
BibTeX
@misc{dc6748eca53d38,
  title = {AgentShield: Fortifying Web Applications Against AI Agents and Agentic Browsers — arXiv:2610.41181},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41181},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6748eca53d38; sha256 526f9b05140cfb2eeb043e7ec880cbb3e00f38a4c472d11d9a366e879dc1ba26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41181. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-powered browser agents are transforming web automation by autonomously interacting with websites and executing complex workflows. However, the effectiveness of existing anti-bot defenses against these systems remains unclear. We present a systematic empirical evaluation of modern agentic browsers against widely deployed anti-bot mechanisms, characterizing their capabilities, limitations, and behavioral differences from humans. Our results show that many defenses designed for traditional automation struggle to reliably detect autonomous AI-driven agents. Accordingly, we introduce AgentShield, a behavioral fingerprinting framework that targets the Perception-Reasoning-Action (PRA) loop underlying agentic user clients. By leveraging dynamic web forms that progressively reveal content and capture fine-grained interaction telemetry, AgentShield exposes behavioral artifacts that enable differentiation between human users and autonomous agents. We further demonstrate Extinction-induced Policy Drift (EPD), a novel attack in which repeated obstruction of task completion causes agents to relax their safeguards and engage in unsafe behaviors. Finally, we present defensive prompt injection techniques that exploit agent-specific weaknesses to mitigate emerging forms of autonomous web abuse that rely on content extraction. Our results highlight both the shortcomings of current web defenses against agentic user clients and the feasibility of practical detection mechanisms tailored to this new generation of web automation.

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/2610.41181 — 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 2026-11-02T04:44:42.672Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).