thunlp / OpenAttack
An Open-Source Package for Textual Adversarial Attack.
☆689Updated last year
Related projects ⓘ
Alternatives and complementary repositories for OpenAttack
- Must-read Papers on Textual Adversarial Attack and Defense☆1,507Updated 2 weeks ago
- Code for EMNLP2020 long paper: BERT-Attack: Adversarial Attack Against BERT Using BERT☆188Updated 4 years ago
- A Model for Natural Language Attack on Text Classification and Inference☆494Updated last year
- Adversarial Training for Natural Language Understanding☆250Updated last year
- Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing☆642Updated 2 years ago
- Natural Language Attacks in a Hard Label Black Box Setting.☆43Updated 3 years ago
- Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"☆85Updated 3 years ago
- TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs…☆2,974Updated 3 months ago
- [ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723☆721Updated 2 years ago
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆151Updated last year
- Summarization Papers☆985Updated last year
- Implementation code for the paper "Generating Natural Language Adversarial Examples"☆167Updated 5 years ago
- Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)☆294Updated 3 months ago
- Prefix-Tuning: Optimizing Continuous Prompts for Generation☆896Updated 6 months ago
- Implementation Code of TextHoaxer☆13Updated 2 years ago
- MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification☆353Updated 4 years ago
- Interpretable Evaluation for AI Systems☆361Updated last year
- CodeBase for Paper: "Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers", / Interactive Demo @☆73Updated last year
- Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)☆138Updated 3 years ago
- ☆394Updated 3 years ago
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆67Updated last year
- TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classifica…☆276Updated 3 months ago
- Bad Characters: Imperceptible NLP Attacks☆35Updated 7 months ago
- [EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach☆296Updated 2 years ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆99Updated last year
- A text generation reading list maintained by Tsinghua Natural Language Processing Group.☆442Updated 4 years ago
- A PyTorch-based knowledge distillation toolkit for natural language processing☆1,601Updated last year
- 简单的向量白化改善句向量质量☆481Updated 3 years ago
- Code associated with the Don't Stop Pretraining ACL 2020 paper☆526Updated 3 years ago
- Tools for checking ACL paper submissions☆598Updated last month