248 robustbench(1) - Kailash Tool Reference
248.1 robustbench
robustbench - RobustBench — standardized adversarial-robustness benchmark suite (model zoo + attacks); MIT code, per-model weight licences vary.
| Layer | DEFENCE |
| Category | d-03-assurance-evals-benchmarks |
| Safety class | safe |
| Licence | MIT |
| Upstream | github.com/RobustBench/robustbench |
248.1.1 NAME
robustbench - RobustBench — standardized adversarial-robustness benchmark suite (model zoo + attacks); MIT code, per-model weight licences vary.
248.1.2 SYNOPSIS & usage
Derived from the upstream README at generation time; verify against --help where the tool is installed.
pip install git+https://github.com/RobustBench/robustbench.gitpip install git+https://github.com/RobustBench/robustbench.git@v1.0248.1.3 DESCRIPTION (upstream)
Francesco Croce* (University of Tübingen), Maksym Andriushchenko* (EPFL), Vikash Sehwag* (Princeton University), Edoardo Debenedetti* (EPFL), Nicolas Flammarion (EPFL), Mung Chiang (Purdue University), Prateek Mittal (Princeton University), Matthias Hein (University of Tübingen) Leaderboard: https://robustbench.github.io/ Paper: https://arxiv.org/abs/2010.09670 ❗Note❗: if you experience problems with the automatic downloading of the models from Google Drive, install the latest version of RobustBench via pip install git+https://github.com/RobustBench/robustbench.git. - May 2022: We have extended
248.1.4 SEE ALSO
- Category: d-03-assurance-evals-benchmarks in the category directory (sister tools listed there).
ref: pin - verified 2026-10-14