mlsanityData to 7 Oct 2026

OpenAttack: An Open-source Textual Adversarial Attack Toolkit

arXiv 2009.09191 ↗First posted 19 Sep 2020cs.CL cs.AI cs.CRcited by 84

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 18; 2023: 23; 2024: 14; 2025: 11; 2026: 2.

84 papers.

Sort:

By area:

  1. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  2. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 227
  3. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 107
  4. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  5. 2023Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Modelscited by 100
  6. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
  7. 2021Evaluating the Robustness of Neural Language Models to Input Perturbationscited by 87
  8. 2022MPCFormer: fast, performant and private Transformer inference with MPCcited by 67
  9. 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Modelscited by 66
  10. 2022Evaluation Gaps in Machine Learning Practicecited by 48
  11. 2023In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPTcited by 35
  12. 2023Using Captum to Explain Generative Language Modelscited by 33
38 more
  1. 2023ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Triggercited by 29
  2. 2021Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Frameworkcited by 27
  3. 2022From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible MLcited by 26
  4. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  5. 2021Multi-granularity Textual Adversarial Attack with Behavior Cloningcited by 21
  6. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Trainingcited by 20
  7. 2022TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalitiescited by 19
  8. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  9. 2021Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Artcited by 18
  10. 2023How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attackscited by 18
  11. 2021BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attackscited by 17
  12. 2022Y-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learningcited by 15
  13. 2022On Robust Prefix-Tuning for Text Classificationcited by 15
  14. 2022Towards Explainable Evaluation Metrics for Natural Language Generationcited by 15
  15. 2024Legilimens: Practical and Unified Content Moderation for Large Language Model Servicescited by 13
  16. 2022Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defensecited by 12
  17. 2023White-Box Multi-Objective Adversarial Attack on Dialogue Generationcited by 12
  18. 2023Generating Valid and Natural Adversarial Examples with Large Language Modelscited by 12
  19. 2023InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanationscited by 11
  20. 2025HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaignscited by 10
  21. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  22. 2023Verifying the Robustness of Automatic Credibility Assessmentcited by 8
  23. 2023An Extensive Study on Adversarial Attack against Pre-trained Models of Codecited by 8
  24. 2021Improving the robustness and accuracy of biomedical language models through adversarial trainingcited by 7
  25. 2023DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimizationcited by 7
  26. 2025FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Modelscited by 7
  27. 2021R&R: Metric-guided Adversarial Sentence Generationcited by 6
  28. 2021Deep learning models are not robust against noise in clinical textcited by 6
  29. 2022ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Datasetcited by 6
  30. 2024ROIC-DM: Robust Text Inference and Classification via Diffusion Modelcited by 5
  31. 2021Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extractioncited by 4
  32. 2022Identifying Adversarial Attacks on Text Classifierscited by 4
  33. 2022Visualizing and Explaining Language Modelscited by 4
  34. 2023Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricingcited by 4
  35. 2024Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varietiescited by 4
  36. 2024OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generationcited by 4
  37. 2024Towards Action Hijacking of Large Language Model-based Agentcited by 4
  38. 2026Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?cited by 4

50 most cited of 84 All 84 (JSON)