Add Backward Smoothing
jinghuichen opened this issue · 3 comments
Paper: Efficient Robust Training via Backward Smoothing https://arxiv.org/abs/2010.01278
Venue: {if applicable, the venue where the paper appeared}
Dataset and threat model: CIFAR-10/CIFAR100, Linf, 8/255
Code: https://github.com/jinghuichen/AutoAttackEval
Pre-trained model: https://drive.google.com/file/d/1lvMa2rbMrIVkAqsyrs_YXLBhewZBfdkP/view?usp=sharing (CIFAR10)
https://drive.google.com/file/d/1xNhK4w5ZuUSfbD_WR4xFKTprojaVux1A/view?usp=sharing (CIFAR100)
Log file: {link to log file of the evaluation}
Additional data: no
Clean and robust accuracy: CIFAR10 clean 85.32 robust 54.94 CIFAR100 clean 62.15 robust 31.92
Architecture: {wideresnet-34-10}
Description of the model/defense: Efficient robust training via backward smoothing
Thanks
Hi,
thanks for the submission! I ran the evaluation with Linf-bound eps=8/255
and got
CIFAR-10
clean accuracy: 85.32%
robust accuracy 51.12%
CIFAR-100
clean accuracy: 62.15%
robust accuracy 26.94%
which seem to me in line with what reported in the paper. If this is the case, I'd be happy to add them!
The numbers are correct. Thank you very much!
Added, thanks again for the submissions!