Fortanix and Nvidia enhance AI model accuracy in drug discovery with Xeureka – SiliconANGLE

A new report out today from Intel Corp.-backed multicloud security firm Fortanix Inc. details how Xeureka Inc., a subsidiary of Mitsui & Co. Ltd., has leveraged Fortanix’s Confidential Computing technology to enhance artificial intelligence model accuracy and reduce drug discovery time and costs.

Since rapidly taking off in 2022 with the release of OpenAI’s ChatGPT, AI has offered great promise across various areas and drug research is one of them. By harnessing the power of AI, pharmaceutical companies can analyze vast datasets with speed and accuracy, potentially leading to the discovery of new drugs at a small fraction of the traditional cost and time.

Xeureka aims to use computer technology across all aspects of drug development to improve the efficiency and effectiveness of new drug research. The use of AI technologies is said to be core to its mission, requiring extensive data sets to power the AI models. However, the data used in pharmaceutical research often includes highly confidential, sensitive and personally identifiable data, while stakeholders must comply with various global privacy regulations.

To tackle the data use issue, Xeureka has partnered with Fortanix and Nvidia Corp. to demonstrate the ability to integrate disparate datasets from multiple sources while maintaining the security and confidentiality of the original sources. Through the partnership, Fortanix provides a control plane to enable security policy management and orchestrate the use of highly confidential data in a secure environment.

Fortanix’s Confidential Computing capabilities include policy management and orchestration of highly confidential data in a secure environment. They also include data sharing and access control for fast and collaborative data processing that ensures privacy for multiple parties without revealing sensitive information.

Modern key management provides unified encryption regardless of data location across hybrid multi-cloud environments and workflow management defines, manages and tracks the data collaboration process flow to ensure privacy and security guardrails are maintained.

Nvidia’s contribution includes secure enclaves and confidential computing graphics processing units for the execution environment. In the environment, data, algorithms and AI models are run to guarantee that highly sensitive data assets remain secure and private while in use.

Through the partnership with Nvidia and Fortanix to enable confidential data collaboration, Xeureka has improved AI model accuracy from 65% to 74%, reducing the time and costs associated with drug discovery. Fortanix also notes that it’s also a proof point for how AI can enhance the effectiveness and efficiency of new drug development while improving the lives of millions of people across the globe.

“This is a perfect example of the power of confidential computing — rapidly processing extremely large volumes of real patient data required by AI models with the highest level of privacy and security possible,” said Anand Kashyap, co-founder and chief executive of Fortanix.

Image: Fortanix