Re:Stanford, USC, Duke study shows AI can read contracts bet...
by wpasc on Monday February 26, 2018 @02:50PM
(#16468362)
I read a great, great paper about training systems against this. Obfuscation is currently easy against AI, but obfuscation that fools an AI and a human could still detect (Purposeful perturbations). This can be pre-trained against by incorporating such perturbations programmatically during training.
Link: https://arxiv.org/pdf/1705.06640.pdf