[EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP

Source code for paper "Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models"

Code for our S&P'21 paper: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding

Code of Robust Lottery Tickets for Pre-trained Language Models (ACL2022)

润学全球官方指定GITHUB，整理润学宗旨、纲领、理论和各类润之实例；解决为什么润，润去哪里，怎么润三大问题； 并成为新中国人的核心宗教，核心信念。

Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-HLT 2021)

Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"

Model interpretability and understanding for PyTorch

Official code and data repository for our EMNLP 2020 long paper "Reformulating Unsupervised Style Transfer as Paraphrase Generation" (https://arxiv.org/abs/2010.05700).

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Code for ACL 2021 paper: Accelerating BERT Inference for Sequence Labeling via Early-Exit

Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)

AI-example-tic-tac-toe functional programming

Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"

The score code of FastBERT (ACL2020)

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)

Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)

Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"

Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".

Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"

主体实现By纸飞机