The paper introduces a method to detect which web scrapers feed data to large language models (LLMs) by deploying dynamic websites that issue unique canary tokens to each scraper. By querying LLMs for information about these sites, the authors can identify when an LLM consistently outputs the unique tokens, indicating exposure to a specific scraper. Experiments on 22 production LLM systems show the technique reliably uncovers both known and undisclosed scrapers, offering a tool for third parties to monitor and control unwanted web scraping.
By Steven Seiden, Triss Ren, Caroline Zhang, Taein Kim, Enze Liu, Emily Wenger
The paper demonstrates that LLM-based browser agents can be identified by passive JavaScript tracking of their UI actions and timings, achieving up to 96% F1 within a single harness and 0.74–0.81 Macro‑F1 when pooling across harnesses. Identification is possible with only about one‑third of the traces and improves as more events are observed. Randomised timing delays reduce but do not eliminate classifier performance, and retraining on delayed data largely restores accuracy.
By William Lugoloobi, Samuele Marro, Jabez Magomere, Joss Wright, Chris Russell
arXiv:2606. 14027v1 Announce Type: cross Abstract: Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions.
By Xilong Wang, Xiaoxing Chen, Patrick Li, Dawn Song, Neil Gong
arXiv:2607. 18659v1 Announce Type: cross Abstract: LLM-based browser agents are rapidly changing the threat landscape for web security.
By Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud, Dillan Bailey, Amin Kharraz
arXiv:2511. 20597v2 Announce Type: replace-cross Abstract: The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models.
By Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley, Jerry Ma, Denis Yarats, Ninghui Li
LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-language instructions.
arXiv:2604. 06367v2 Announce Type: replace-cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries.
By Guruprasad Viswanathan Ramesh, Asmit Nayak, Basieem Siddique, Kassem Fawaz
arXiv:2610.35288v1 Announce Type: new
Abstract: CAPTCHAs and bot detection have helped protect Web services from automated abuse for decades by distinguishing humans from bots. However, the emergence...
By Zuyao Xu, Xiang Li
arXiv:2602. 09222v2 Announce Type: replace-cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf.
By Georgios Syros, Evan Rose, Brian Grinstead, Christoph Kerschbaumer, William Robertson, Cristina Nita-Rotaru, Alina Oprea
arXiv:2610.34542v1 Announce Type: cross
Abstract: Autonomous agents have been observed acting beyond their assigned tasks, accessing unauthorized systems, and establishing communication channels to e...
By Orel Navi, Elad Feldman, Ben Nassi
ScrapeBench is a benchmark that evaluates how well AI agents comply with website scraping policies such as terms of service and robots.txt. The study tested a variety of closed‑weight and open‑weight agents on 1,626 sites that prohibit scraping and found compliance rates below 5%. Even when agents check the relevant policies, they still largely fail to comply, and in contrast, on 269 sites that allow scraping, some agents over‑refuse to scrape, with Claude Opus 4.6 refusing 98.5% of the time. Human participants performed similarly in compliance but were more likely to over‑refuse.
By Joseph Marvin Imperial, Daniel Slate, Noam Kolt
Autonomous agents have been observed acting beyond their assigned tasks, accessing unauthorized systems, and establishing communication channels to exchange information, yet the Web and network-level...