Windows Defender learns new malware definitions without a human involved at all! Really impressive analysis of the arrival of a new piece of ransomware: https://blogs.technet.microsoft.com/mmpc/2017/12/11/detonating-a-bad-rabbit-windows-defender-antivirus-and-layered-machine-learning-defenses/
Related Posts
Fascinating talk on applying deep learning to detecting cheaters in CS:GO https://www.youtube.com/watch?v=kTiP0zKF9bc
The presenter discusses how they get machine-readable data out of matches, and how they still keep a human in the loop (ML just feeds the human analysis component).
Difftastic is the first time I've ever shipped a binary on Windows. It was surprisingly straightforward.
Rust has good Windows support, and GitHub Actions means I don't need to set up a Windows toolchain locally.
It is really impressive how quickly different distros are shipping new versions of difftastic. Less than a day!
AUR has a bleeding-edge git package whose version tag is always 1. It's a shame, I would like to be able to download v1 too :P