The security threats of neural networks and deep learning algorithms


This article is part of Demystifying AI, a series of posts that (try to) disambiguate the jargon and myths surrounding AI. History shows that cybersecurity threats evolve along with new technological advances. Relational databases brought SQL injection attacks, web scripting programming languages spurred cross-site scripting attacks, IoT devices ushered in new ways to create botnets, and the internet in general opened a Pandora’s box of digital security ills. Social media created new ways to manipulate people through micro-targeted content delivery and made it easier to gather information for phishing attacks. And bitcoin enabled the delivery of crypto-ransowmare attacks. The list goes on. The point is, every…

This story continues at The Next Web


Go to Source