Leileileisa

advance_software_dev_pj

高级软件开发微服务项目

AI-example-tic-tac-toe

AI-example-tic-tac-toe functional programming

AWP

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

awt

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

BkdAtk-LWS

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

captum

Model interpretability and understanding for PyTorch

DNFCalculating

主体实现By纸飞机

DRW

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

Embedding-Poisoning

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

FastBERT

The score code of FastBERT (ACL2020)

Leileileisa/advance_software_dev_pj

高级软件开发微服务项目

Leileileisa/AI-example-tic-tac-toe

AI-example-tic-tac-toe functional programming

Leileileisa/AWP

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

Leileileisa/awt

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

Leileileisa/BkdAtk-LWS

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

Leileileisa/captum

Model interpretability and understanding for PyTorch

Leileileisa/DNFCalculating

主体实现By纸飞机

Leileileisa/DRW

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

Leileileisa/Embedding-Poisoning

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

Leileileisa/FastBERT

The score code of FastBERT (ACL2020)

Leileileisa/HiddenKiller

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

Leileileisa/Iter-CoT

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

Leileileisa/LeisaCtp

A simple CTP realization.

Leileileisa/NeuBA

Leileileisa/PABEE

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

Leileileisa/QuickFix

A simple realization of quickfix

Leileileisa/RAP

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

Leileileisa/RIPPLe

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

Leileileisa/robust_ticket

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

Leileileisa/run

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**人的核心宗教，核心信念。

Leileileisa/Sequence-Labeling-Early-Exit

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

Leileileisa/SimCSE

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

Leileileisa/SOS

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

Leileileisa/style-transfer-paraphrase

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

Leileileisa/StyleAttack

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

Leileileisa/Tcp

A simple realization of tcp server/client

Leileileisa/ThreadPool

A simple realization of ThreadPool

Leileileisa/transformers

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