Google llc (20240346367). Privacy-Preserving Learning and Analytics of a Shared Embedding Space Across Multiple Separate Data Silos simplified abstract

Privacy-Preserving Learning and Analytics of a Shared Embedding Space Across Multiple Separate Data Silos

Organization Name

google llc

Inventor(s)

Animesh Nandi of Cupertino CA (US)

Liam Charles Macdermed of Millbrae CA (US)

Privacy-Preserving Learning and Analytics of a Shared Embedding Space Across Multiple Separate Data Silos - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240346367 titled 'Privacy-Preserving Learning and Analytics of a Shared Embedding Space Across Multiple Separate Data Silos

The patent application describes systems and methods for privacy-preserving learning and analytics of a shared embedding space for data split across multiple separate data silos.

• A central computing system generates synthetic data examples with feature data within an aggregate feature-space representing an aggregation of different component feature-spaces associated with the separate data silos.
• The synthetic data examples are used by different computing systems to generate embeddings within a shared embedding space.
• Analytics can be performed on the shared embedding space, such as identifying or classifying malicious actors across multiple separate entity domains.

1. 1. 1. Potential Applications:

This technology can be applied in various industries such as cybersecurity, healthcare, finance, and marketing for secure data analysis and classification.

1. 1. 1. Problems Solved:

The technology addresses the challenge of analyzing data across multiple separate silos while maintaining privacy and security.

1. 1. 1. Benefits:

- Enhanced privacy protection - Secure data analysis - Improved classification accuracy

1. 1. 1. Commercial Applications:

The technology can be utilized by cybersecurity firms, healthcare organizations, financial institutions, and marketing agencies for secure data analysis and classification, leading to better decision-making and risk management.

1. 1. 1. Prior Art:

Readers can explore prior research on privacy-preserving data analysis and secure machine learning techniques to understand the evolution of this technology.

1. 1. 1. Frequently Updated Research:

Stay updated on advancements in privacy-preserving machine learning techniques and secure data analysis methods to enhance the effectiveness of this technology.

1. 1. 1. 1. Questions about Privacy-Preserving Learning and Analytics:

1. How does this technology ensure the privacy of data across multiple separate silos? 2. What are the key advantages of using a shared embedding space for data analysis and classification?

Original Abstract Submitted

provided are systems and methods for privacy-preserving learning and analytics of a shared embedding space for data split across multiple separate data silos. a central computing system can generate a plurality of synthetic data examples having respective feature data within an aggregate feature-space that represents an aggregation of different component feature-spaces associated with the multiple separate data silos. the synthetic data examples can be used by different computing systems associated with the data silos to generate embeddings within a shared embedding space. once the embeddings have been generated in the shared embedding space, multiple different types of analytics can be performed on the shared embedding space. as one example, the multiple data silos can correspond to multiple separate entity domains and an analysis of embeddings generated in the shared embedding space can be used to facilitate identification or classification of malicious actors across the multiple separate entity domains.