Open access
Jul 2026
METHODS FOR COUNTERING DATA POISONING DURING THE FINE-TUNING PHASE OF NEURAL NETWORKS
A multi-loop protection system which protects the latent feature space through mathematical validation and guarantees the structural integrity of neural network models when transfer learning is applied in high-risk domains.
Oleksandr Kushnerov, S. Yevseiev, D. Tymofieiev et al.
· Advanced Information Systems · 0 citations