OpenAttack: An Open-source Textual Adversarial Attack Toolkit
This toolkit addresses the problem of hindered utilization and fair comparison of attack models for researchers and practitioners in adversarial machine learning, though it is incremental as it builds on existing models.
The authors tackled the lack of standardization and comparability in textual adversarial attack models by developing OpenAttack, an open-source toolkit that supports all attack types, multilinguality, and parallel processing, including 15 typical models.
Textual adversarial attacking has received wide and increasing attention in recent years. Various attack models have been proposed, which are enormously distinct and implemented with different programming frameworks and settings. These facts hinder quick utilization and fair comparison of attack models. In this paper, we present an open-source textual adversarial attack toolkit named OpenAttack to solve these issues. Compared with existing other textual adversarial attack toolkits, OpenAttack has its unique strengths in support for all attack types, multilinguality, and parallel processing. Currently, OpenAttack includes 15 typical attack models that cover all attack types. Its highly inclusive modular design not only supports quick utilization of existing attack models, but also enables great flexibility and extensibility. OpenAttack has broad uses including comparing and evaluating attack models, measuring robustness of a model, assisting in developing new attack models, and adversarial training. Source code and documentation can be obtained at https://github.com/thunlp/OpenAttack.