Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach
A dual-locking method for securing trained neural networks, combining key-driven index permutation with personal identification number-based watermarking via sparse quantization index modulation (QIM), which offers strong protection and traceability for neural network models.
Iva Vasic, Jesús Muñoz-Cádiz, Bata Vasic
· IEEE Transactions on Artific... · 0 citations