News for hackers. Stuff that matters.
Re:Researchers easily trick Cylance's AI Antivirus to think ... by solveit on Friday July 19, 2019 @02:39AM (#20476611)
Many ML successes look exactly like that.
Re:Researchers easily trick Cylance's AI Antivirus to think ... by Barrin92 on Friday July 19, 2019 @05:53AM (#20477302)
that's mostly because the bar is so unbelievably low that "it works 95% of the time" is good enough to please consumers. In security or anything that requires engineering rigor where catching the exception is exactly what matters ML is virtually useless, or even worse actively harmful.
Re:Researchers easily trick Cylance's AI Antivirus to think ... by jointpdf on Friday July 19, 2019 @07:33AM (#20477715)
That’s not true, there’s an entire subfield of stats/ML dedicated to anomaly detection.
Re:Researchers easily trick Cylance's AI Antivirus to think ... by Barrin92 on Friday July 19, 2019 @12:17PM (#20479894)
But even outliers in ML systems are pretty much always outliers of first order, that is to say they're outliers in a predictable way, they're often significantly different from their environment.

The sort of outliers that concern security problems are pretty much always idiosyncratic by design because the people that create them know how easy it is to create adversarial examples for machines.

There's a human ingenuity to genuine edge cases that ML is ill suited to figure out because ML by design draws conclusions from patterns. My prediction is that we'll very soon see the same problem in fields like autonomous driving. Every time we see ML attack complex human domains, the "last 2%" seem intractable.