Organizations are turning to machine learning solutions to help identify malware, Sven Krasser, PhD, chief scientist at CrowdStrike, wrote in an op-ed for CIO Dive.
By embedding machine learning, a security product is able to detect some new threats, even when traditional malicious indicators are missing, Dr. Krasser wrote. However, he warned against depending on machine learning, in part because training the algorithm to detect entirely unknown threats is challenging.
"Such systems can perform well on new variants of a known family, but they will fail when presented with an unknown malware family," he wrote, noting the WannaCry ransomware attack as a noteworthy example.
"An attacker has months worth of time to craft malware while an anti-malware engine generally needs to come to a decision in a sub-second timeframe. Without observing the execution, there will always be malware files that manage to sneak by undetected — that is a fact that machine learning does not change," he added.
Click here to read the full article.
More articles on health IT:
3 thoughts on e-prescriptions with Surescripts' Paul Uhrig
NIH awards $3.3M grant for cardiac precision medicine study
Is artificial intelligence what the doctor ordered?