At #ISC2026 today (9 AM CET; Session 7B), #softwaresecurity researcher Suphannee Sivakorn shares independent research showing that she broke Google’s #reCAPTCHA visual challenges 92.6% of the time (500 sessions) w/ free, #opensource, local #AI models t.co/PL2zBuiuoU (1/4) t.co/VabwL48GlM
This is the second time Sivakorn has cracked #reCAPTCHA! 10 years ago, she was part of a @Columbia team that conducted the first #deeplearning-based attack on it. Read their original paper from Black Hat Asia 2016: t.co/iqQJWKzZ2a #BHAsia #cybersecurity (2/4) t.co/T6fYkgDMmq
@Columbia @BlackHatEvents Read Sivakorn's new paper from Information Security Conference 2026 (#ISC2026), co-authored with #softwaresecurity researcher Samantha Gottlieb: "Robot Visions: Breaking #reCAPTCHA at Zero Cost and Zero Shot" t.co/LRS5ZpqPoI (3/4) t.co/73Yr0Fk8ff
@Columbia @BlackHatEvents Their research paper also states that these findings were disclosed to Google in September 2026, prior to the paper's publication #reCAPTCHA (4/4)
