AI for cybersecurity is a hot new thing—and a dangerous gamble

Machine learning can help guard against cyberattacks, but hackers can foil security algorithms by targeting the data they train on.

Some background: The security industry is facing a tsunami of cyberattacks just as the number of devices being hooked up to the internet is exploding. At the same time, there’s a massive shortage of skilled cyber workers.

Data dangers: Firms are rushing to roll out machine-learning-based products, but in their haste they could be using training information that hasn’t been thoroughly scrubbed of anomalous data points or corrupted data. That could lead to algorithms missing some attacks.

The solution: None of this means that AI and machine learning shouldn’t have an important role in a defensive arsenal. But as our own Martin Giles writes, experts say it’s really important for security companies to monitor and minimize the risks associated with algorithmic models.

Quelle: technologyreview.com