Had always thought it would come to this. Mentioned it in a talk I gave in the 90s. But how well and how soon? As long as there are malicious developers out there, sooner than we thought.
This Company Uses AI to Outwit Malicious AI in Wired
Robust Intelligence is among a crop of companies that offer to protect clients from efforts at deception.
IN SEPTEMBER 2019, the National Institute of Standards and Technology issued its first-ever warning for an attack on a commercial artificial intelligence algorithm.
Security researchers had devised a way to attack a Proofpoint product that uses machine learning to identify spam emails. The system produced email headers that included a “score” of how likely a message was to be spam. But analyzing these scores, along with the contents of messages, made it possible to build a clone of the machine-learning model and craft spam messages that evaded detection. ... "
No comments:
Post a Comment