
Armory-library is a library for evaluating adversarial attack machine learning models. It is a pure Python installable which is intended to be used in a user created application. The armory-library API is intentionally small and simple to afford "today" speed of integration. Armory-library uses PyTorch, Lightning.AI, and IBM's Adversarial Robustness Toolbox (ART) to effect its evaluations; it logs all pararmeters and metrics to MLFlow either locally or to a remote server. Armory-library is part of the Armory project.
If you use this software, please cite it using the metadata from this file.
adversarial machine learning
adversarial machine learning
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
