To promote innovation in fully homomorphic encryption (FHE), IBM® researchers have initiated challenges on the FHERMA platform for FHE challenges launched in late 2023 by Fair Math and the OpenFHE community.
FHE: A new frontier in technology
Fully homomorphic encryption is a revolutionary technology with vast potential. One of its significant applications is in enhancing medical AI models. By facilitating seamless collaboration among various research institutes in the training process, FHE paves the way for a new era of possibilities. The capability to process encrypted data without decryption signifies a crucial advancement that has the potential to transform various fields.
IBM has been at the forefront of advancing FHE for 15 years, ever since IBM Research scientist Craig Gentry introduced the first feasible fully homomorphic scheme in 2009. The “bootstrapping” mechanism he developed cleans and reduces the amount of “noise” in encoded information, enabling the widespread commercial use of FHE.
Progress in FHE
FHE has made significant progress since the introduction of its initial scheme. The shift from theoretical frameworks to practical implementations has been accompanied by numerous challenges that need to be tackled. While there are already applications utilizing FHE, the community is continuously enhancing and innovating algorithms to make FHE more popular and applicable to new domains.
Fostering innovation through challenges
The FHERMA platform was created to incentivize innovation in the FHE domain. Various challenges can be found on the FHERMA site, inspired by issues encountered in real-world machine learning and blockchain applications.
Solutions to challenges must be developed using established cryptographic libraries like openFHE. Developers can also utilize higher-level libraries such as IBM’s HElayers to expedite their development process and write robust, generic code with ease.
The top solutions to the challenges will receive cash prizes from Fair Math, in addition to contributing to the FHE community. Winners will also have the opportunity to showcase their solutions in an upcoming workshop.
The objective of the challenges is to promote research, popularize FHE, and create cryptographic primitives that are efficient, generic, and support various hyperparameters (e.g., efficient matrix multiplication for matrices of dimensions 1000×1000 and 10×10). This aligns with IBM’s vision for privacy-preserving computation using FHE.
Driving progress and adoption
Engaging in and solving challenges listed on the FHERMA site is an exciting and rewarding way to further the widespread adoption of FHE while advancing development and research in the field. We encourage you to join us in this exciting initiative on the FHERMA challenges platform.
Teams and individuals who successfully solve the challenges will receive cash prizes from Fair Math. More importantly, the innovative solutions to the challenges will propel the FHE community forward, a longstanding goal for IBM.
Explore IBM HElayers today
Was this article helpful?
YesNo
