Adversarial NLP Robustness NLP Tools

Tools, datasets, and methods for generating adversarial attacks on NLP models, evaluating model robustness, and developing defense mechanisms against adversarial perturbations. Does NOT include general model evaluation, bias detection without adversarial intent, or data augmentation for improving performance.

There are 43 adversarial nlp robustness tools tracked. 1 score above 50 (established tier). The highest-rated is thunlp/OpenAttack at 58/100 with 772 stars.

Get all 43 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=nlp&subcategory=adversarial-nlp-robustness&limit=20"

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

#	Tool	Score	Tier	Stars	Language
1	thunlp/OpenAttack An Open-Source Package for Textual Adversarial Attack.	58	Established	772	Python
2	thunlp/TAADpapers Must-read Papers on Textual Adversarial Attack and Defense	49	Emerging	1,574	Python
3	jind11/TextFooler A Model for Natural Language Attack on Text Classification and Inference	47	Emerging	529	Python
4	thunlp/OpenBackdoor An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022...	43	Emerging	200	Python
5	thunlp/SememePSO-Attack Code and data of the ACL 2020 paper "Word-level Textual Adversarial...	41	Emerging	88	Python
6	osoleve/glitchlings Enemies for your LLM	41	Emerging	35	Python
7	thunlp/HiddenKiller Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual...	41	Emerging	43	Python
8	thunlp/Advbench Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations...	38	Emerging	72	Python
9	aonotas/adversarial_text Code for Adversarial Training Methods for Semi-Supervised Text Classification	38	Emerging	124	Python
10	thunlp/BkdAtk-LWS Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable...	38	Emerging	16	Python
11	lancopku/Avg-Avg [Findings of EMNLP 2022] Holistic Sentence Embeddings for Better...	37	Emerging	18	Python
12	salesforce/adversarial-polyglots Code for the paper "Code-Mixing on Sesame Street: Dawn of the Adversarial...	37	Emerging	10	Python
13	SecHack365-Fans/prompt2slip This library is testing the ethics of language models by using natural...	34	Emerging	9	Python
14	INK-USC/RobustLR A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners	34	Emerging	8	Python
15	pramodkaushik/np_analysis Adversarial attacks generated for the ACL paper "Did the Model Understand...	33	Emerging	8	Jupyter Notebook
16	mirbostani/RobustQA RobustQA: A Framework for Adversarial Text Generation Analysis on Question...	33	Emerging	8	Python
17	pramodkaushik/acl18_results Code to reproduce results in our ACL 2018 paper "Did the Model Understand...	31	Emerging	33	—
18	snowood1/BERT-ENN Uncertainty-Aware Reliable Text Classification (KDD 2021)	31	Emerging	18	Jupyter Notebook
19	thunlp/RobTest Source code for ACL 2023 Findings paper "From Adversarial Arms Race to...	28	Experimental	8	Python
20	LCS2-IIITD/HIT-ACL2021-Codemixed-Representation This repo contains the source code of HIT: A Hierarchically Fused Deep...	27	Experimental	6	Python
21	ruizheng20/robust_data Codes for the ACL Findings paper "Characterizing the Impacts of Instances on...	24	Experimental	5	Python
22	alekseevskaia/OrderBkd Backdoor attack in NLP	22	Experimental	2	Python
23	xinzhel/attack_alta Experiment for the paper published on ALTA2021: "Exploring the Vulnerability...	21	Experimental	1	Python
24	3f1P3c4n1/Literary-LLM-Knowledge-Data-Poisoning Data poisoning attacks on LLMs — corrupting Harry Potter knowledge via...	21	Experimental	1	Jupyter Notebook
25	leonardodalinky/zero-shot-GLS [NAACL'24] ZGLS: Zero-shot Generative Linguistic Steganography	21	Experimental	9	Python
26	gallilmaimon/LUNATC This is the official implementation of "A Universal Adversarial Policy for...	21	Experimental	9	Python
27	YangLinyi/GLUE-X We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU...	21	Experimental	93	Python
28	lancopku/DAN [Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based...	21	Experimental	12	Python
29	claws-lab/multimodal-robustness Code and resources for EMNLP 2022 paper on 'Robustness of Fusion-based...	20	Experimental	10	Python
30	chong-z/nlp-second-order-attack [NAACL 2021] Code for "Double Perturbation: On the Robustness of Robustness...	20	Experimental	8	Python
31	princeton-nlp/rationale-robustness NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790	19	Experimental	27	Python
32	Samanth-ai/robust-transformer-qa-adversarial-inoculation Transformer-based extractive QA robustness: adversarial distractor...	19	Experimental	—	Python
33	jrohsc/MSDT Code of the IEEE UV2022 accepted paper "MSDT: Masked Language Model Scoring...	19	Experimental	3	Python
34	REACT-NLP/tcab_generation Code to generate and extend the TCAB dataset.	19	Experimental	3	Python
35	nishiwen1214/AT_Papers Must-read papers on Adversarial training for neural networks！	19	Experimental	12	—
36	lexicalcomputing/hamod a High Agreement Multi-lingual Outlier Detection dataset	19	Experimental	4	Python
37	95anantsingh/NYU-Attacking-Compressed-NLP Testing transferability of Adversarial samples across NLP models.	17	Experimental	1	Jupyter Notebook
38	yul091/DGSlow Codebase for the ACL 2023 paper: White-Box Multi-Objective Adversarial...	14	Experimental	16	Python
39	Raibows/RMLM RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level...	13	Experimental	9	Python
40	Yangyi-Chen/MAYA Code base for the EMNLP 2021 paper, "Multi-granularity Textual Adversarial...	13	Experimental	13	Python
41	xingyizhao/TAMPERS Code associated with Findings of EMNLP (2022) paper "Generating Textual...	12	Experimental	7	Python
42	HenryPengZou/DeCrisisMB [EMNLP 2023] Official Code of "DeCrisisMB: Debiased Semi-Supervised Learning...	12	Experimental	6	Python
43	karanparekh14/ADTA5760--Group-4 Contaminated knowledge base of 150 academic PDFs (450 contaminants) for LLM...	11	Experimental	—	HTML