The problem The previous post in our series discussed techniques for providing input privacy in PPFL systems where data is horizontally partitioned. This blog will focus on techniques for providing input privacy when data is vertically partitioned . As described in our third post , vertical partitioning is where the training data is divided across parties such that each party holds different columns of the data. In contrast to horizontally partitioned data, training a model on vertically partitioned data is more challenging as it is generally not possible to train separate models on different
Related Posts
With the new year under way, NIST is continuing to…
- rooter
- February 8, 2024
- 1 min read
- 0
A new, sophisticated malware toolkit called Decoy Dog was discovered…
- rooter
- May 2, 2023
- 1 min read
- 0
The initial public draft of NIST Special Publication (SP) 800-201,…
- rooter
- February 15, 2023
- 1 min read
- 0
In November 2022, ChatGPT launched, bringing new possibilities and challenges.…
- rooter
- August 21, 2024
- 1 min read
- 0