Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"
☆40Nov 3, 2021Updated 4 years ago
Alternatives and similar repositories for ONION
Users that are interested in ONION are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆46Sep 11, 2022Updated 4 years ago
- Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"☆48Oct 12, 2022Updated 4 years ago
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆44Jul 26, 2021Updated 5 years ago
- Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"☆16Jun 29, 2021Updated 5 years ago
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆25Oct 21, 2021Updated 5 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks☆13Feb 26, 2023Updated 3 years ago
- Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)☆142Sep 22, 2025Updated last year
- Code for the paper "Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks"☆14Aug 22, 2022Updated 4 years ago
- KNN Defense Against Clean Label Poisoning Attacks☆13Sep 24, 2021Updated 5 years ago
- Natural Perturbation for Robust Question Answering☆12Apr 7, 2020Updated 6 years ago
- ☆26Apr 15, 2021Updated 5 years ago
- ☆33Mar 4, 2022Updated 4 years ago
- ☆10Apr 15, 2023Updated 3 years ago
- pytorch版损失函数，改写自科学空间文章，【通过互信息思想来缓解类别不平衡问题】、【将“softmax+交叉熵”推广到多标签分类问题】☆12Aug 22, 2021Updated 5 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆12Dec 20, 2024Updated last year
- Evaluate QA models for consistency☆20Nov 21, 2022Updated 3 years ago
- Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)☆15Oct 8, 2020Updated 6 years ago
- This is AlpaGasus2-QLoRA based on LLaMA2 with AlpaGasus mechanism using QLoRA!☆15Nov 22, 2023Updated 2 years ago
- ☆11Oct 3, 2021Updated 5 years ago
- ☆19Feb 10, 2022Updated 4 years ago
- [COLING25] CodeJudge Eval: Can Large Language Models be Good Judges in Code Understanding?☆12Dec 3, 2024Updated last year
- ☆32Apr 14, 2023Updated 3 years ago
- ☆26Jul 19, 2022Updated 4 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- N/A☆19Aug 15, 2022Updated 4 years ago
- Data and code for "Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models", which accepted in TSE.☆16Jul 3, 2024Updated 2 years ago
- ☆27Feb 9, 2022Updated 4 years ago
- Code of the COLING22 paper "uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers"☆19Aug 17, 2022Updated 4 years ago
- Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking☆13Feb 5, 2023Updated 3 years ago
- ☆13Nov 7, 2023Updated 2 years ago
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆15Nov 19, 2025Updated 11 months ago
- This is the project repository of our ASE22 paper: Natural Test Generation for Precise Testing of Question Answering Software☆14Dec 1, 2022Updated 3 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Feb 27, 2020Updated 6 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Constrained Decoding Project☆20Nov 10, 2023Updated 2 years ago
- ☆25Aug 21, 2024Updated 2 years ago
- The CodeInsight dataset is designed for code generation tasks, providing developers with expert-curated examples that bridge the gap betw…☆15Oct 22, 2024Updated 2 years ago
- List of Papers on Attack and Defense (AD) in AI Models☆29Mar 18, 2022Updated 4 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆21Aug 10, 2024Updated 2 years ago
- ☆15Jan 19, 2020Updated 6 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆20Jun 7, 2023Updated 3 years ago