News for hackers. Stuff that matters.
Re:Google AI invents its own cryptographic algorithm by Strilanc on Friday October 28, 2016 @01:42PM (#12818622)
Outputting floats instead of discrete values actually sounds like a very exploitable hole to me.

It reminds me of the classic "check if your model corresponds to reality" example where a one-time pad is broken: the standard said "<0.5V volts is OFF" but your machine was outputting 0.1V for OFFs that came from computing 0 xor 0 and 0.2V for OFFs that came from computing 1 xor 1.

There are no comments on this comment yet.