| Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text | May 25, 2023 | Adversarial RobustnessClassification | —Unverified | 0 |
| From Shortcuts to Triggers: Backdoor Defense with Denoised PoE | May 24, 2023 | backdoor defenseData Poisoning | CodeCode Available | 0 |
| Two-in-One: A Model Hijacking Attack Against Text Generation Models | May 12, 2023 | ClassificationFace Recognition | —Unverified | 0 |
| Masked Language Model Based Textual Adversarial Example Detection | Apr 18, 2023 | Adversarial DefenseLanguage Modeling | CodeCode Available | 0 |
| TrojText: Test-time Invisible Textual Trojan Insertion | Mar 3, 2023 | SST-2 | CodeCode Available | 0 |
| Few-shot Multimodal Multitask Multilingual Learning | Feb 19, 2023 | Few-Shot LearningIn-Context Learning | —Unverified | 0 |
| Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE | Feb 18, 2023 | Contrastive LearningDenoising | —Unverified | 0 |
| BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing | Jan 25, 2023 | Backdoor AttackSentence | —Unverified | 0 |
| RPN: A Word Vector Level Data Augmentation Algorithm in Deep Learning for Language Understanding | Dec 12, 2022 | CoLAData Augmentation | CodeCode Available | 0 |
| Uncertainty Sentence Sampling by Virtual Adversarial Perturbation | Oct 26, 2022 | Active LearningDiversity | —Unverified | 0 |
