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.
@article{arxiv.2602.22238,
title = {TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI},
author = {Kyeongpil Min and Sangmin Jeon and Jae-Jin Lee and Woojoo Lee},
journal= {arXiv preprint arXiv:2602.22238},
year = {2026}
}
Comments
8 pages, 7 figures, 3 tables. This paper has been accepted at Design Automation Conference (DAC) 2026