Compactness+Robustness · Issue #7 · fra31/auto-attack (original) (raw)

Paper: https://arxiv.org/pdf/2002.10509.pdf

Venue: {if applicable, the venue where the paper appeared}

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

Code: https://github.com/inspire-group/compactness-robustness. A minimal script to evaluate a WRN-28-10 model is available at https://gist.github.com/VSehwag/688632e523df5d2a4c8008f5ee567b1c (only need to download the checkpoint)

Pre-trained model: https://www.dropbox.com/sh/56yyfy16elwbnr8/AADmr7bXgFkrNdoHjKWwIFKqa?dl=0 Use the model_best_dense.pth.tar

Log file: {link to log file of the evaluation}

Additional data: yes

Clean and robust accuracy: Benign test accuracy = 88.97% , PGD-50 test accuracy (1-restart) = 62.24%, Auto-attack (cheap): 57.88%

Architecture: WRN-28-10 (90% connections pruned)

Description of the model/defense: Compressed neural networks while simultaneously aching high robustness.