Researchers Easily Trick Cylance's AI-Based Antivirus Into Thinking Malware Is 'Goodware' July 18, 2019 https://www.vice.com/en_us/article/...d-antivirus-into-thinking-malware-is-goodware Cylance, I Kill You!
BlackBerry Cylance to rush out a fix for anti-virus bypass exploit July 19, 2019 https://www.computing.co.uk/ctg/news/3079287/blackberry-cylance-security-patch
Nothing really new. There are plenty of Cylance by-passes like this one: https://www.mdsec.co.uk/2019/03/silencing-cylance-a-case-study-in-modern-edrs/ . You just have to look for them.
As I always said here Ai is just marketing trick to appeal noobs. Ai alone can't do much compared to other and even older solutions.
I believe this is a quite painful exploit, I had high hopes for AI. But this might seriously damage the way people see AI and machine learning. Or perhaps Cylance simply didn't design it properly. I believe this article is not about exploiting AI, but they bypassed Cylance behavior monitoring part.
Cylance Antivirus Products Susceptible to Concatenation Bypass Vulnerability Note VU#489481 August 1, 2019 https://kb.cert.org/vuls/id/489481/