Scholarlink

Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end workflow for automating privacy-preserving inference queries including the detection of subqueries that involve AI/ML model inferences on sensitive attributes. Our proposed novel declarative privacy-preserving workflow allows users to specify “what private information to protect” rather than “how to protect”. Under the hood, the system automatically chooses privacy-preserving plans and hyper-parameters. Link to our video: https://youtu.be/nK2deY_6adM

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Declarative Privacy-Preserving Inference Queries

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Hong Guan,
  • Ansh Tiwari,
  • Summer Gautier,
  • Rajan Hari Ambrish,
  • Lixi Zhou,
  • Yancheng Wang,
  • Deepti Gupta,
  • Yingzhen Yang,
  • Chaowei Xiao,
  • Kanchan Chowdhury,
  • Jia Zou

摘要

Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end workflow for automating privacy-preserving inference queries including the detection of subqueries that involve AI/ML model inferences on sensitive attributes. Our proposed novel declarative privacy-preserving workflow allows users to specify “what private information to protect” rather than “how to protect”. Under the hood, the system automatically chooses privacy-preserving plans and hyper-parameters. Link to our video: https://youtu.be/nK2deY_6adM