search

fra31 / auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
https://arxiv.org/abs/2003.01690
MIT License
626 stars 111 forks source link

Width-Adjusted-Regularization Update #40

Open tabrisweapon opened 3 years ago

tabrisweapon commented 3 years ago

Paper: { http://arxiv.org/abs/2010.01279 }

Venue: {unpublished}

Dataset and threat model: {CIFAR-10, l-inf, eps=8/255, AutoAttack}

Code: {Same with the last report}

Pre-trained model: {https://www.dropbox.com/s/89i5zoxa2ugglaq/wrn-34-15-cad59.pt?dl=0 }

Log file: {None}

Additional data: {yes}

Clean and robust accuracy: {clean:87.67%, AutoAttack: 60.65%}

Architecture: {WideResNet-34-15}

Description of the model/defense: ’‘’ Dear authors of AutoAttack: This is an update for our last submission in https://github.com/fra31/auto-attack/issues/21. Here we report our new best results and hope to replace it with the current one on the table (the 4th one). We also change our title from "Does Network Width Really Help Adversarial Robustness?" to "Do Wider Neural Networks Really Help Adversarial Robustness?". Please update this information for us on the RobustBench too.

Thanks! Boxi Wu ‘’‘

fra31 commented 3 years ago

Hi,

thanks for sharing your new model! I've updated the entry. I'll also change the title on RobustBench.

tabrisweapon commented 3 years ago

Hi,

thanks for sharing your new model! I've updated the entry. I'll also change the title on RobustBench.

Thanks!