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.

Debuting at the FHE.org 2026 Conference, the Gentry–Lee (GL) scheme introduces a breakthrough in matrix multiplication performance for Fully Homomorphic Encryption.

SEOUL, South Korea and TAIPEI, March 8, 2026 /PRNewswire/ -- DESILO, a deep-tech company specializing in privacy-enhancing technologies, today unveiled the Gentry–Lee (GL) scheme, a major advancement positioned as the 5th generation of Fully Homomorphic Encryption (FHE).

The scheme is being formally presented at the FHE.org 2026 Conference in Taipei. The framework is co-authored by Yongwoo Lee (Chief Scientist, DESILO) and Craig Gentry (Chief Scientist, Cornami) — the inventor of FHE in 2009 and recipient of the 2022 Gödel Prize.

As organizations increasingly adopt AI while handling sensitive data, a new paradigm known as Private AI is emerging. Private AI enables AI systems to operate directly on encrypted data, allowing enterprises and organizations to use AI without exposing sensitive prompts, inputs, or model outputs to the AI provider.

This capability is particularly important for highly regulated industries, enterprise environments with strict data protection and sovereignty requirements, and organizations working with highly sensitive or valuable data.

Fully Homomorphic Encryption (FHE) enables this approach by allowing computations to be performed directly on encrypted data without decrypting it.

While earlier FHE schemes made encrypted computation increasingly practical, their computational overhead has remained a major challenge for modern AI workloads. The GL scheme introduces a new architecture designed to significantly improve the efficiency of matrix multiplication, one of the core operations underlying modern deep learning systems.

Because Large Language Models (LLMs) rely heavily on repeated matrix multiplication, improving this operation is critical for enabling AI computation under encryption.

"Back in the early days of FHE, the primary goal was proving mathematical feasibility," said Craig Gentry, Chief Scientist of Cornami. "With the GL scheme, we are fundamentally restructuring how homomorphic operations handle matrix multiplication. Optimizing these core operations brings encrypted computation much closer to supporting modern AI architectures."

"Matrix multiplication is the dominant workload in modern AI systems," said Yongwoo Lee, Chief Scientist of DESILO. "With the GL scheme, we introduce a new framework designed to significantly improve how these operations are performed under homomorphic encryption, bringing practical Private AI closer to reality."

The full research paper describing the GL scheme is available via the IACR ePrint archive.

Technical paper:
https://eprint.iacr.org/2025/1935

FHE.org 2026 Conference:
https://fhe.org/conferences/conference-2026/

Learn more about DESILO and Private AI:
https://desilo.ai

Media Contact
Howard Park
Co-founder / CSO
contact@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, 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.