thunlp/TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
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.
Stars
1,574
Forks
194
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
thunlp/OpenAttack
An Open-Source Package for Textual Adversarial Attack.
jind11/TextFooler
A Model for Natural Language Attack on Text Classification and Inference
thunlp/OpenBackdoor
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
thunlp/SememePSO-Attack
Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial...
osoleve/glitchlings
Enemies for your LLM