Pinned Repositories
awesome-knowledge-graph
整理知识图谱相关学习资料
backdoor-learning-resources
A list of backdoor learning resources
BackdoorBench
BackdoorBox
BadEncoder
badnets
Implementation of badnets on CIFAR10 and MNIST
badnets-pytorch
Simple PyTorch implementations of Badnets on MNIST and CIFAR10.
clean_label_textual_backdoor_attack
d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被55个国家的300所大学用于教学。
T-Miner
wmuog's Repositories
wmuog/backdoor-learning-resources
A list of backdoor learning resources
wmuog/BadEncoder
wmuog/d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被55个国家的300所大学用于教学。
wmuog/T-Miner
wmuog/BackdoorBench
wmuog/BackdoorBox
wmuog/clean_label_textual_backdoor_attack
wmuog/awesome-active-learning
A curated list of awesome Active Learning
wmuog/Awesome-ML-SP-Papers
A curated list of Meachine learning Security & Privacy papers published in security top-4 conferences (IEEE S&P, ACM CCS, USENIX Security and NDSS).
wmuog/EmbMarker
Code and data for our paper "Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark" in ACL 2023.
wmuog/GPT_API_free
Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。
wmuog/incubator-mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
wmuog/invisible_backdoor_attacks
wmuog/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
wmuog/llm_interview_note
大模型面试题及答案，大模型八股文
wmuog/naturalcc
NaturalCC: An Open-Source Toolkit for Code Intelligence
wmuog/One-to-One-WebSockets-Chat
Building Persistable One-to-One Chat Using Spring Boot and WebSockets
wmuog/OpenBackdoor
An open-source toolkit for textual backdoor attack and defense
wmuog/OpenDelta
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)
wmuog/OpenRLHF
A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
wmuog/paper-reading
深度学习经典、新论文逐段精读
wmuog/Refool
wmuog/SOS
Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
wmuog/SpeechGPT
SpeechGPT Series: Speech Large Language Models
wmuog/StyleAttack
Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"
wmuog/text2vec
text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。
wmuog/TextAttack
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
wmuog/ThesisUESTC
ThesisUESTC-电子科技大学毕业论文模板
wmuog/TrojanNet-1
This is the Pytorch implementation of TrojanNet: Embedding Hidden Trojan Horse Models in Neural Networks.
wmuog/Warping-based_Backdoor_Attack-release
WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)