Blog keyword search

VB2017 preview: Stuck between a ROC and a hard place

We preview the VB2017 paper by Microsoft's Holly Stewart and Joe Blackbird, which uses data about users switching anti-virus provider to decide whether machine-learning models should favour avoiding false positives over false negatives.
Authors of security software in general, and anti-virus software in particular, have always needed to find the right balance between a high detection rate and a low false positive…

We have placed cookies on your device in order to improve the functionality of this site, as outlined in our cookies policy. However, you may delete and block all cookies from this site and your use of the site will be unaffected. By continuing to browse this site, you are agreeing to Virus Bulletin's use of data as outlined in our privacy policy.