Agreed. Like many of our networks. We didn't build with adversarial agents in mind.
Securing machine learning models to be hacker-proof will be the next frontier in cybersecurity.https://www.wired.com/story/researcher-fooled-a-google-ai-into-thinking-a-rifle-was-a-helicopter/ …
-
-
-
This has worried me a lot with driverless cars. Difficult to predict how exploit will manifest. But if exploited systematically, big problem.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.