Collected research

Measuring and Analyzing Search Engine Poisoning of Linguistic Collisions

Matthew Joslin, Neng Li, Shuang Hao, Minhui Xue and Haojin Zhu · doi.org

Misspellings that happen to be real words, often in another language, slip past search engines' auto-correction, so attackers can rank malicious pages against those queries. A crawl of 1.77 million misspelled searches on Google and Baidu, with a neural model to pick candidates, finds about 1.19 percent return malicious first-page results, concentrated in gambling, drugs and adult terms.

Record

Researcher

Matthew Joslin, Neng Li, Shuang Hao, Minhui Xue and Haojin Zhu

Published by

doi.org

Topic

Other

In the archive

• Collected in the 2019 research round

Related sources

• Measuring and Analyzing Search Engine Poisoning of Linguistic Collisions

Tags

• typosquatting
• measurement-study
• large-scale-scan
• detection
• owasp-a06-2021
• owasp-a09-2021

This page is the archive's own catalogue record. The research is the work of Matthew Joslin, Neng Li, Shuang Hao, Minhui Xue and Haojin Zhu, first published at the original source. Preserved copies are kept so the citation survives its host; this one was last captured on 14 August 2026.