OpenAttack

topic-trees

project-slogans

project slogan short

An Open-Source Package for Textual Adversarial Attack.

project slogan long

OpenAttack is an open-source Python-based textual adversarial attack toolkit, which handles the whole process of textual adversarial attacking, including preprocessing text, accessing the victim model, generating adversarial examples and evaluation.

_images/logo-small.png

project-features

project-feature-1

_images/全部.svg

All-type Support

OpenAttack supports all types of attacks including sentence-/word-/character-level perturbations and gradient-/score-/decision-based/blind attack models;

project-feature-2

_images/多语言.svg

Multilinguality

OpenAttack supports English and Chinese now. Its extensible design enables quick support for more languages

project-feature-3

_images/并行数据挖掘.svg

Parallel processing

OpenAttack provides support for multi-process running of attack models to improve attack efficiency

project-feature-4

_images/huggingface.png

Compatibility with 🤗

OpenAttack is fully integrated with 🤗 Transformers and Datasets libraries;

project-feature-5

_images/可扩展性强.svg

Extensibility

You can easily attack a customized victim model on any customized dataset or develop and evaluate a customized attack model.

data-results

Uses

data result list

_images/Align_baseline+row.svg

Attack Baseline

_images/攻击.svg

Attack Evaluation

_images/开发套件.svg

Develop New Attack Models

_images/盾牌.svg

Evaluate Robustness

_images/训练.svg

Adversarial Training