An End-to-End Homomorphically Encrypted Neural Network
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915174986809344 |
|---|---|
| author | Florencio, Marcos Alencar, Luiz Lima, Bianca |
| author_facet | Florencio, Marcos Alencar, Luiz Lima, Bianca |
| contents | Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic encryption, which allows the neural network to operate on encrypted data. We show that Homomorphic Neural Networks (HNN) can achieve full privacy and security while maintaining levels of accuracy comparable to plain neural networks. We also introduce a new layer, the Differentiable Soft-Argmax, which allows the calibration of output logits in the encrypted domain, raising the entropy of the activation parameters, thus improving the security of the model, while keeping the overall noise below the acceptable noise budget. Experiments were conducted using the Stanford Sentiment Treebank (SST-2) corpora on the DistilBERT base uncased finetuned SST-2 English sentiment analysis model, and the results show that the HNN model can achieve up to 82.5% of the accuracy of the plain model while maintaining full privacy and security. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16176 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An End-to-End Homomorphically Encrypted Neural Network Florencio, Marcos Alencar, Luiz Lima, Bianca Cryptography and Security Artificial Intelligence Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic encryption, which allows the neural network to operate on encrypted data. We show that Homomorphic Neural Networks (HNN) can achieve full privacy and security while maintaining levels of accuracy comparable to plain neural networks. We also introduce a new layer, the Differentiable Soft-Argmax, which allows the calibration of output logits in the encrypted domain, raising the entropy of the activation parameters, thus improving the security of the model, while keeping the overall noise below the acceptable noise budget. Experiments were conducted using the Stanford Sentiment Treebank (SST-2) corpora on the DistilBERT base uncased finetuned SST-2 English sentiment analysis model, and the results show that the HNN model can achieve up to 82.5% of the accuracy of the plain model while maintaining full privacy and security. |
| title | An End-to-End Homomorphically Encrypted Neural Network |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2502.16176 |