|
|
|
|
|
|
by wpasc
3033 days ago
|
|
|
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 |
|
|