Collected research
The Failure of Noise-Based Non-Continuous Audio Captchas
An S&P 2011 paper presenting a generic pipeline that breaks audio CAPTCHAs built from non-continuous speech, combining audio processing with machine learning. The authors report success against every popular scheme of the period, including Microsoft's and Yahoo's. Only the abstract is archived here; the paper and slides remain as PDFs on the publisher's CDN.
Record
- Researcher
- Elie Bursztein, Romain Bauxis, Hristo Paskov, Daniele Perito, Celine Fabry and John C. Mitchell
- Published by
- elie.net
- Topic
- Other
In the archive
Tags
This page is the archive's own catalogue record. The research is the work of Elie Bursztein, Romain Bauxis, Hristo Paskov, Daniele Perito, Celine Fabry and John C. Mitchell, first published at the original source. Preserved copies are kept so the citation survives its host; this one was last captured on .