thunlp / OpenAttackLinks
An Open-Source Package for Textual Adversarial Attack.
☆740Updated 2 years ago
Alternatives and similar repositories for OpenAttack
Users that are interested in OpenAttack are comparing it to the libraries listed below
Sorting:
- Must-read Papers on Textual Adversarial Attack and Defense☆1,561Updated 2 months ago
- A Model for Natural Language Attack on Text Classification and Inference☆514Updated 2 years ago
- Code for EMNLP2020 long paper: BERT-Attack: Adversarial Attack Against BERT Using BERT☆199Updated 4 years ago
- Natural Language Attacks in a Hard Label Black Box Setting.☆47Updated 4 years ago
- Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing☆647Updated 2 years ago
- Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"☆87Updated 4 years ago
- CodeBase for Paper: "Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers", / Interactive Demo @☆78Updated 2 years ago
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆71Updated 2 years ago
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆185Updated 2 years ago
- TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs…☆3,233Updated last month
- ☆11Updated 5 years ago
- Implementation Code of TextHoaxer☆14Updated 2 years ago
- Adversarial Training for Natural Language Understanding☆251Updated last year
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆34Updated 3 years ago
- Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)☆295Updated last year
- AutoPrompt: Automatic Prompt Construction for Masked Language Models.☆629Updated 11 months ago
- Code for ACL2018 HotFlip: White-Box Adversarial Examples for Text Classification, Word-level Adversarial Examples☆36Updated 6 years ago
- [ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723☆728Updated 2 years ago
- Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"☆43Updated 2 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Updated 2 years ago
- Code for Natural Language Adversarial Attacks and Defenses in Word Level☆8Updated 5 years ago
- [DEPRECATED] Repo for exploring multi-task learning approaches to learning sentence representations☆808Updated 4 years ago
- Collection of papers and resources for data augmentation for NLP.☆829Updated 2 years ago
- Bad Characters: Imperceptible NLP Attacks☆35Updated last year
- Implementation code for the paper "Generating Natural Language Adversarial Examples"☆170Updated 5 years ago
- codes for paper "learning to discriminate perturbations for blocking adversarial attacks in text classification" in EMNLP19☆15Updated 5 years ago
- Hidden backdoor attack on NLP systems☆47Updated 3 years ago
- ☆18Updated 4 years ago
- A Query Efficient Natural Language Attack in a Black Box Setting☆16Updated 3 years ago
- collection of the SOTA linguistic steganalysis methods☆25Updated last year