Identifying AI Web Scrapers Using Canary Tokens
Open Access
- 14 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 6998-7012
Abstract
No abstract availableFunding Information
- Google academic research award (None)
This publication has 15 references indexed in Scilit:
- Rethinking Web Cache Design for the AI Era2025
- Scrapers Selectively Respect robots.txt Directives: Evidence From a Large-Scale Empirical Study2025
- Somesite I Used To Crawl: Awareness, Agency and Efficacy in Protecting Content Creators From AI Crawlers2025
- Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models2024
- A Longitudinal Study of Content Control Mechanisms2024
- Web Scraping or Web Crawling: State of Art, Techniques, Approaches and ApplicationInternational Journal of Advances in Soft Computing and its Applications, 2021
- Good Bot, Bad Bot: Characterizing Automated Browsing Activity2021
- Bot Detection Model using User Agent and User Behavior for Web Log AnalysisProcedia Computer Science, 2020
- Detecting malicious activities with user‐agent‐based profilesInternational Journal of Network Management, 2015
- A large-scale study of robots.txt2007