-
Notifications
You must be signed in to change notification settings - Fork 4
Open
Labels
Description
此 ISSUE 为 [隐语开源共建计划(SecretFlow Open Source Contribution Plan,简称 SF OSCP)Phase 6 任务 ISSUE,欢迎社区开发者参与共建~
- 认领前,辛苦确认是否完成[报名](https://studio.secretflow.com/activity/rkub4eryy7g3vmn/detail
- 更多任务,可查看 「OSCP Phase6 Season of Dev」Project
This ISSUE is one of the tasks of the [SecretFlow Open Source Contribution Plan (referred to as SF OSCP) Phase 6. Welcome to join us in building it together!
- Before claiming a task, please make sure you have signed up.
- For more tasks, you can check the "OSCP Phase6 Season of Dev" Project.
任务介绍
- 任务名称:拆分学习 SPlitGuard 防御优化算法实现
- 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 SPlitGuard 防御优化算法实现,实现拆分学习图数据的特征攻击算法实现,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
操作说明
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
Type
Projects
Status
In progress