研究提出多层指纹识别方法，可区分 AI 网页智能体与人类及传统爬虫

View PDF HTML (experimental)

Abstract:As AI web agents proliferate, combining large language models with autonomous, browser-level control, indiscriminate content scraping by web agents has emerged as a privacy and security challenge. Existing defenses, such as this http URL and active bot-blocking, are insufficient, as they are widely violated and easily circumvented. In this work, we demonstrate that AI web agents can be effectively distinguished from humans and traditional crawlers using a multi-layer fingerprint based on both network layer characteristics (e.g., TLS, HTTP) and browser interaction behavior. We implement this mechanism as a programmatic logging framework that can be deployed on a live, instrumented domain.
By analyzing six prominent agent frameworks (AutoGen, Browser Use, Claude, Gemini, ChatGPT, and Skyvern), we uncover latent structural differences in how these systems assemble HTTP requests, establish TLS/HTTP connections, and execute autonomous browser actions. Feeding these multi-layer features into a decision tree classifier, our framework achieves high-fidelity identification (100% accuracy), successfully isolating distinct agent architectures and differentiating agent traffic from both human browsing baselines and legacy crawlers. Our findings demonstrate that cross-layer agent tracking provides a robust approach to content protection and web security policy enforcement.

Subjects:	Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2606.20910 [cs.CR]
	(or arXiv:2606.20910v2 [cs.CR] for this version)
	https://doi.org/10.48550/arXiv.2606.20910 arXiv-issued DOI via DataCite

Submission history

From: Dayeon Kang [view email]
[v1] Thu, 18 Jun 2026 20:07:39 UTC (10,045 KB)
[v2] Wed, 11 Nov 2026 16:32:50 UTC (3,528 KB)