[ICML 2023] Official code implementation of "Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning (https://proceedings.mlr.press/v202/dai23a)"

[Usenix Security 2024] Official code implementation of "BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning" (https://www.usenix.org/conference/usenixsecur…

Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)

A collection of Google research projects related to Federated Learning and Federated Analytics.

Federated averaging algorithm and centralized training

Lime: Explaining the predictions of any machine learning classifier

PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)

自身学习的安全数据科学和算法的学习资料

📁 #AISecurity

TCL-TencentCloudListener 腾讯云抢占式实例监听器

Code for Data Poisoning Attacks Against Federated Learning Systems

High-performance, scalable time-series database designed for Industrial IoT (IIoT) scenarios

PyTorch implementation of Federated Learning with Non-IID Data, and federated learning algorithms, including FedAvg, FedProx.

An advanced web directory & file scanning tool that will be more powerful than DirBuster, Dirsearch, cansina, and Yu Jian.一个高级web目录、文件扫描工具，功能将会强于DirBuster、Dirsearch、cansina、御剑。

python3写的综合扫描工具，主要用来存活验证，敏感文件探测(目录扫描/js泄露接口/html注释泄露)，WAF/CDN识别，端口扫描，指纹/服务识别，操作系统识别，POC扫描，SQL注入，绕过CDN，查询旁站等功能，主要用来甲方自测或乙方授权测试，请勿用来搞破坏。

ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341

远控免杀系列文章及配套工具，汇总测试了互联网上的几十种免杀工具、113种白名单免杀方式、8种代码编译免杀、若干免杀实战技术，并对免杀效果进行了一一测试，为远控的免杀和杀软对抗免杀提供参考。

A repository for learning various heap exploitation techniques.

一个Vulhub漏洞复现知识库

漏洞靶场-快速搭建Web安全漏洞和第三方组件漏洞环境，用于漏洞复现和研究

一个搬运工项目，分享一点点之前看过的文档/结构图/思维导图/ppt/电子书

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o…

Byzantine-resilient distributed SGD with TensorFlow.

Code for the paper "Sniper Backdoor: Single Client Targeted Backdoor Attack in Federated Learning". SaTML'23.