Descriptor:
Overview
Overview
Authors
Affiliations
Affiliations
Soon will be listed here.
Abstract
To uniformly test and benchmark the secure evaluation of transformer-based models, we designed the iDASH24 homomorphic encryption track dataset. The dataset comprises a protein family classification model with a transformer architecture and an example dataset that is used to build and test the secure evaluation strategies. This dataset was used in the challenge period of iDASH24 Genomic Privacy Competition, where the teams designed secure evaluation of the classification model using a homomorphic encryption scheme. Combined with the benchmarking results and companion methods, iDASH24 dataset is a unique resource that can be used to benchmark secure evaluation of neural network models.
References
1.
Kertesz-Farkas A, Dhir S, Sonego P, Pacurar M, Netoteia S, Nijveen H
. Benchmarking protein classification algorithms via supervised cross-validation. J Biochem Biophys Methods. 2007; 70(6):1215-23.
DOI: 10.1016/j.jbbm.2007.05.011.
View
2.
Wan Z, Hazel J, Clayton E, Vorobeychik Y, Kantarcioglu M, Malin B
. Sociotechnical safeguards for genomic data privacy. Nat Rev Genet. 2022; 23(7):429-445.
PMC: 8896074.
DOI: 10.1038/s41576-022-00455-y.
View
3.
Kuo T, Jiang X, Tang H, Wang X, Harmanci A, Kim M
. The evolving privacy and security concerns for genomic data analysis and sharing as observed from the iDASH competition. J Am Med Inform Assoc. 2022; 29(12):2182-2190.
PMC: 9667175.
DOI: 10.1093/jamia/ocac165.
View
4.
Mistry J, Chuguransky S, Williams L, Qureshi M, Salazar G, Sonnhammer E
. Pfam: The protein families database in 2021. Nucleic Acids Res. 2020; 49(D1):D412-D419.
PMC: 7779014.
DOI: 10.1093/nar/gkaa913.
View
5.
Sonego P, Pacurar M, Dhir S, Kertesz-Farkas A, Kocsor A, Gaspari Z
. A Protein Classification Benchmark collection for machine learning. Nucleic Acids Res. 2006; 35(Database issue):D232-6.
PMC: 1669728.
DOI: 10.1093/nar/gkl812.
View