Machine learning attacks against the Asirra CAPTCHA 论文
2008引用 233
User Authentication and Security SystemsBiometric Identification and SecurityAdvanced Malware Detection Techniques
摘要
The Asirra CAPTCHA [EDHS2007], proposed at ACM CCS 2007, relies on the problem of distinguishing images of cats and dogs (a task that humans are very good at). The security of Asirra is based on the presumed difficulty of classifying these images automatically.