Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[特别任务] 拆分学习主动数据重构攻击 FSHA 算法实现,及其对应的 DP 防御方法 #767

Open
Candicepan opened this issue Jul 21, 2023 · 1 comment · May be fixed by #1147
Assignees
Labels
challenge SecretFlow Open Source Contribution Plan OSCP SecretFlow Open Source Contribution Plan

Comments

@Candicepan
Copy link
Contributor

此 ISSUE 为 隐语开源共建计划(SecretFlow Open Source Contribution Plan,简称 SF OSCP)第二期任务 ISSUE 合作任务,合作开发者可完成,其他开发者欢迎点击这里,选择其他你感兴趣的任务,热烈欢迎社区开发者参与共建~

任务介绍

  • 任务名称:拆分学习主动数据重构攻击 FSHA 算法实现,及其对应的 DP防 御方法
  • 技术方向:Federated Learning/Split Learning
  • 任务难度:挑战🌟🌟🌟

详细要求

结合 SLModel 拆分学习主动数据重构攻击 FSHA 算法实现,及其对应的 DP防 御方法,进行封装实验和实验报告。

  • 安全性:尽量少 reveal
  • 功能性:可完整实现某个拆分学习攻防算法的全流程
  • 收敛性:包含 simulator 跑出的实验数据并且证明攻击/防御效果
  • 代码规范:Python 代码需要使用 black+isort 进行格式化(流水线包含代码规范检查卡点)
  • 提交说明:关联该 issue 并提交代码至 https://github.com/secretflow/secretflow/tree/main/examples/security

能力要求

  • 网空项目-拆分学习攻防参与同学

操作说明

@Candicepan Candicepan added OSCP SecretFlow Open Source Contribution Plan challenge SecretFlow Open Source Contribution Plan labels Jul 21, 2023
@PingyiHu
Copy link

PingyiHu give it to me

@Candicepan Candicepan changed the title [特别任务] 拆分学习主动数据重构攻击 FSHA 算法实现,及其对应的 DP防 御方法 [特别任务] 拆分学习主动数据重构攻击 FSHA 算法实现,及其对应的 DP 防御方法 Nov 3, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
challenge SecretFlow Open Source Contribution Plan OSCP SecretFlow Open Source Contribution Plan
Projects
Status: In Progress
2 participants