secml: A Python Library for Secure and Explainable Machine Learning

42 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Adversarial Detection of Flash Malware: Limitations and Open Issues (2017, methodology): “ and Training Procedures We used the popular machine-learning suite scikit-learn [68], which features the classiers used in our evaluation,8 as well as secml to simulate evasion attacks against them [69]. All the performed evaluations (except the temporal evaluation and the one against obfuscated ma”
RobustBench: a standardized adversarial robustness benchmark (2020, background): “Recent works have already referred to our 346 leaderboards [68, 147, 80, 122, 143], in particular as reflecting the current state of the art [100, 75, 94], 347 and used the networks of our Model Zoo to test new adversarial attacks [83, 104, 38, 108], to evaluate 348 test-time defenses [131] or to ev”