thunlp/TAADpapers

Must-read Papers on Textual Adversarial Attack and Defense

49
/ 100
Emerging

This resource curates a comprehensive list of must-read academic papers focused on how to intentionally trick Natural Language Processing (NLP) models and how to make them more resilient. It organizes research on creating "adversarial attacks" that fool systems, along with methods for "defense" to improve model robustness. Researchers and practitioners in machine learning and AI ethics would use this to understand vulnerabilities and build more reliable text-based AI.

1,574 stars. No commits in the last 6 months.

Use this if you are an NLP researcher, data scientist, or ML engineer looking for a categorized collection of academic papers to understand or implement textual adversarial attacks and defense strategies.

Not ideal if you are looking for an introductory guide to NLP or pre-built, production-ready tools for immediate deployment without deeper academic research.

Natural Language Processing AI Safety Machine Learning Robustness Adversarial AI Computational Linguistics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,574

Forks

194

Language

Python

License

MIT

Last pushed

Jun 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/thunlp/TAADpapers"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.