OpenAttack: An Open-source Textual Adversarial Attack Toolkit

Abstract

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.

arXiv commentACL-IJCNLP 2021 Demo. 9 pages, 3 figures

References in corpus (11)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Exploring the Limits of Language Modeling
• BAE: BERT-based Adversarial Examples for Text Classification
• Generating Natural Adversarial Examples
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Synthetic and Natural Noise Both Break Neural Machine Translation
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Foolbox: A Python toolbox to benchmark the robustness of machine learning models
• Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
• Advbox: a toolbox to generate adversarial examples that fool neural networks

Cited by in corpus (12)

• Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art
• On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
• ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset
• TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
• Adversarial Attack Classification and Robustness Testing for Large Language Models for Code
• Verifying the Robustness of Automatic Credibility Assessment
• Deep learning models are not robust against noise in clinical text
• Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks
• R&R: Metric-guided Adversarial Sentence Generation
• Towards Robustness Analysis of E-Commerce Ranking System
• Multi-granularity Textual Adversarial Attack with Behavior Cloning
• Evaluating the Robustness of Neural Language Models to Input Perturbations