TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917294812168192 |
|---|---|
| author | Min, Kyeongpil Jeon, Sangmin Lee, Jae-Jin Lee, Woojoo |
| author_facet | Min, Kyeongpil Jeon, Sangmin Lee, Jae-Jin Lee, Woojoo |
| contents | Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encryption studies largely assume dense weights, leaving its practicality under TTD compression unclear. We present TT-SEAL, a selective-encryption framework for TT-decomposed networks. TT-SEAL ranks TT cores with a sensitivity-based importance metric, calibrates a one-time robustness threshold, and uses a value-DP optimizer to encrypt the minimum set of critical cores with AES. Under TTD-aware, transfer-based threat models (and on an FPGA-prototyped edge processor) TT-SEAL matches the robustness of full (black-box) encryption while encrypting as little as 4.89-15.92% of parameters across ResNet-18, MobileNetV2, and VGG-16, and drives the share of AES decryption in end-to-end latency to low single digits (e.g., 58% -> 2.76% on ResNet-18), enabling secure, low-latency edge AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22238 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI Min, Kyeongpil Jeon, Sangmin Lee, Jae-Jin Lee, Woojoo Cryptography and Security Artificial Intelligence Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encryption studies largely assume dense weights, leaving its practicality under TTD compression unclear. We present TT-SEAL, a selective-encryption framework for TT-decomposed networks. TT-SEAL ranks TT cores with a sensitivity-based importance metric, calibrates a one-time robustness threshold, and uses a value-DP optimizer to encrypt the minimum set of critical cores with AES. Under TTD-aware, transfer-based threat models (and on an FPGA-prototyped edge processor) TT-SEAL matches the robustness of full (black-box) encryption while encrypting as little as 4.89-15.92% of parameters across ResNet-18, MobileNetV2, and VGG-16, and drives the share of AES decryption in end-to-end latency to low single digits (e.g., 58% -> 2.76% on ResNet-18), enabling secure, low-latency edge AI. |
| title | TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.22238 |