Belfort Launches Hardware Accelerator for Encrypted Compute

Sep 24, 2025
Belfort, a KU Leuven spin-off, has announced the launch of the world's first hardware accelerator for encrypted compute, alongside a $6 million seed funding round led by Vsquared Ventures.

Belfort, a spin-off from KU Leuven, has announced the launch of the world's first hardware accelerator designed for encrypted compute, as well as the successful close of a $6 million seed funding round. The funding was led by deep-tech specialist Vsquared Ventures, with participation from several other investors, including high-profile figures like Google's Chief Scientist Jeff Dean and Naval Ravikant. This financial boost will enable Belfort to expand its team, advance product development, and support early enterprise pilots in its San Francisco and Leuven offices, announced in a press release.

Belfort's technology allows for data processing without decryption, addressing the need for secure data handling in various sectors such as blockchain, finance, healthcare, and government operations. The hardware accelerator removes performance barriers traditionally associated with encrypted computation, making large-scale deployment feasible. Already available on AWS Marketplace, this innovation is built on years of research from KU Leuven's COSIC lab, led by Prof. Ingrid Verbauwhede, a global authority in cryptographic hardware.

The founding team includes Laurens De Poorter, Dr. Furkan Turan, Michiel Van Beirendonck, and Prof. Ingrid Verbauwhede, who bring extensive experience from organizations like Google[x], Intel, Microsoft Research, and Rambus. Their work has been supported by major European Research Council grants and a competitive U.S. government contract with DARPA.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Funding Brief, Silicon Brief or Daily AI Brief.

Free newsletter

AI Funding Brief

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.