Desilo to launch HARVEST in December,
enabling secure, privacy-preserving collaboration for faster, efficient
healthcare research.
Seoul,
South Korea: Desilo Inc., a privacy-focused technology
startup specializing in cryptographic data collaboration, has announced plans
to launch its new healthcare platform, HARVEST, this December. The platform is
designed to enable medical institutions and pharmaceutical companies to
collaborate on research while ensuring sensitive patient data remains
protected.
The sharing of large,
multi-institutional datasets is often critical for medical research, but
stringent privacy regulations and security risks have posed significant
challenges. According to IBM, the average cost of a healthcare data breach is USD
10.93 million, while violations of Europe’s GDPR can result in penalties of up
to EUR 20 million. Desilo aims to tackle these challenges by leveraging Fully
Homomorphic Encryption (FHE) and Federated Learning (FL), allowing joint data
analysis and model training without ever exposing raw data.
The company claims that studies that
previously took months can now be completed in about a week using HARVEST,
significantly boosting research efficiency. The platform supports horizontal
and vertical FL, split learning, and cohort federation, while automatically
managing compliance with GDPR and HIPAA regulations.
"Pharmaceutical companies and
research consortia often face a tradeoff between privacy and progress," said Seungmyung Lee, Chief
Executive of Desilo. "Our mission is to shorten research timelines and
reduce development costs—ultimately helping accelerate drug development and
diagnoses without compromising patient privacy."
The startup has further been selected
for several government-backed initiatives, including Korea’s National Cancer
Center Safe Data Zone Project, highlighting its growing influence in
privacy-preserving healthcare technologies.
According to TechSci Research, the launch of HARVEST by Desilo is set
to bring significant benefits to the healthcare industry by addressing
longstanding challenges in secure data sharing. Medical research often relies
on large, multi-institutional datasets, but strict privacy regulations and
security concerns have limited collaboration. HARVEST leverages Fully
Homomorphic Encryption (FHE) and Federated Learning (FL), allowing researchers
and pharmaceutical companies to jointly analyze data without exposing sensitive
patient information. This ensures compliance with regulations such as GDPR and
HIPAA while reducing the risk of costly data breaches. By accelerating studies
that traditionally took months to just a week, the platform enhances research
efficiency and shortens drug development timelines. Additionally, its support
for horizontal and vertical FL, split learning, and cohort federation enables
more robust, collaborative studies. Overall, HARVEST has the potential to
advance healthcare innovation while maintaining the highest standards of data
privacy.