Characterizing homology-induced data leakage and memorization in genome-trained sequence models

Characterizing homology-induced data leakage and memorization in genome-trained sequence models

Characterizing homology-induced data leakage and memorization in genome-trained sequence models By Nadya Karpova January 5, 2026 Characterizing homology-induced data leakage and memorization in genome-trained sequence models Abdul Muntakim Rafi University of British Columbia Abstract: Models that predict function from DNA sequence have become critical tools in deciphering the roles of genomic sequences and genetic variation within them. However,…