So far, we have some really weird results where PGD and Autoattack are getting really low 0-1% accuracy, inconsistent with existing published papers.
We don't think this is due to a bug in our code; our normalization and quantization handling should be solidified at this point.
We propose the following
So far, we have some really weird results where PGD and Autoattack are getting really low 0-1% accuracy, inconsistent with existing published papers.
We don't think this is due to a bug in our code; our normalization and quantization handling should be solidified at this point.We propose the following