 |
SEOUL, South Korea, April 28, 2026 /PRNewswire/ — DESILO, a pioneering deep-tech company specializing in privacy-enhancing technologies, has announced the release of the world’s first Fully Homomorphic Encryption (FHE) library to seamlessly integrate the 5th-generation ‘GL Scheme (Gentry-Lee Scheme)’. This breakthrough marks a monumental step forward in making ‘Private AI’—the ability to train and run advanced AI models directly on encrypted data—a practical reality.
Fully Homomorphic Encryption is widely considered the holy grail of data security, allowing computations to be performed on data without ever decrypting it. However, earlier generations of FHE faced massive computational bottlenecks, particularly when handling matrix multiplication, which serves as the mathematical engine of modern deep learning.
Debuted at the FHE.org 2026 Conference in Taipei, the GL scheme was co-authored by Craig Gentry, the original inventor of FHE, and Yongwoo Lee, Chief Scientist of DESILO.
This 5th-generation architecture fundamentally restructures homomorphic operations to optimize matrix multiplication, solving the computational overhead that previously hindered encrypted AI workloads.
The newly updated DESILO FHE Library is the first commercially available framework to successfully bring the GL scheme from theory into high-performance execution. Built natively on C++ and CUDA, the library is rigorously optimized for both CPUs and NVIDIA GPUs. It features a dual-scheme architecture: supporting the RNS-CKKS scheme for vector operations and the revolutionary GL scheme for matrix operations. To ensure frictionless adoption, the library provides a robust Python wrapper, making it exceptionally accessible for data scientists to integrate into existing ML workflows.
“Matrix multiplication is the dominant workload in modern AI systems,” said Yongwoo Lee, Chief Scientist of DESILO. “With our new library natively supporting the GL scheme, we are fundamentally restructuring how these critical operations are performed under homomorphic encryption. We are closing the gap between theoretical security and practical AI deployment.”
By breaking down the performance barriers of encrypted data processing, DESILO’s latest milestone empowers highly regulated sectors—such as finance, healthcare, and enterprise data analytics—to unlock the full disruptive potential of AI without compromising data privacy or running afoul of global regulatory compliance.
The DESILO FHE Library:
https://fhe.desilo.dev/latest/
Technical paper:
https://eprint.iacr.org/2025/1935
FHE.org 2026 Conference:
Presentation: https://www.youtube.com/watch?v=VA9s6I9KmA0
Slides: https://fhe.org/conferences/conference-2026/resources/slides/0910_Lee.pdf
Learn more about DESILO and Private AI:
https://desilo.ai
About DESILO
DESILO is a deep-tech company advancing the future of Private AI through breakthroughs in cryptography. Specializing in Fully Homomorphic Encryption (FHE) and privacy-enhancing technologies (PET), DESILO develops infrastructure that enables AI systems to operate securely on encrypted data, allowing organizations to unlock the value of sensitive data without compromising privacy.
