robustbench icon indicating copy to clipboard operation
robustbench copied to clipboard

RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]

Results 19 robustbench issues
Sort by recently updated
recently updated
newest added

When loading imagenetc with a batchsize of over 5k images, you always get 5k images back. This doesn't throw out an error, and it can be confusing when you expect...

enhancement

# Paper Information - **Paper Title**: Deeper Insights into the Robustness of ViTs towards Common Corruptions - **Paper URL**: https://arxiv.org/abs/2204.12143 - **Paper authors**: Rui Tian, Zuxuan Wu, Qi Dai, Han...

new-model

# Paper Information - **Paper Title**: Data filtering for efficient adversarial training - **Paper URL**: https://doi.org/10.1016/j.patcog.2024.110394 - **Paper authors**: Erh-Chung Chen, Che-Rung Lee # Leaderboard Claim(s) ## Model 1 -...

new-model

Hi RobustBench authors, thank you very much for creating and maintaining this platform. We would like to submit a new model. # Paper Information - **Paper Title**: MixedNUTS: Training-Free Accuracy-Robustness...

new-model

Hi, Thanks for creating this repository. I just had one request: Could we add the Standard model for CIFAR100? Like a WideResNet28-10, just like how it exists for CIFAR10? The...

When loading a model, it downloads from Google Drive, it downloads a .pt file but just contains html content of download verification page like the following screenshot. And then, it...

- Update venue for Bai2024MixedNUTS https://github.com/RobustBench/robustbench/issues/169 - Update venue and model for Cui2023Decoupled https://github.com/RobustBench/robustbench/issues/197 - Temporary fix for `timm`version https://github.com/RobustBench/robustbench/issues/196

# Paper Information - **Paper Title**: Decoupled Kullback-Leibler Divergence Loss - **Paper URL**: https://arxiv.org/pdf/2305.13948 - **Paper authors**: Jiequan Cui, Zhuotao Tian, Zhisheng Zhong, Xiaojuan Qi, Bei Yu, Hanwang Zhang #...

new-model

# Paper Information - **Paper Title**: MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification - **Paper URL**: https://arxiv.org/pdf/2406.05927 - **Paper authors**: Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr #...

new-model