BROWSE
Detail
Conference Paper
TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI
- Authors
- Kyeongpil Min, Sangmin Jeon, Jae-Jin Lee, Woojoo Lee
- Issue Date
- 2026-07
- Citation
- Design Automation Conference (DAC) 2026, pp.1-7
- Publisher
- ACM
- Language
- English
- Type
- Conference Paper
- Abstract
- 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.
- Keyword
- model compression, tensor-train decomposition, selective encryp- tion, adversarial robustness, edge AI, FPGA prototyping
- KSP Keywords
- As 4, Black box, End to End(E2E), FPGA prototyping, Low Latency, Model compression, Selective encryption, Sensitivity-based, Threat model, Time robustness, Transfer-based
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
