SPOILER: TEE-Shielded DNN Partitioning of On-Device Secure Inference with Poison Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915839468371968 |
|---|---|
| author | Kang, Donghwa Choe, Hojun Kim, Doohyun Baek, Hyeongboo Kang, Brent ByungHoon |
| author_facet | Kang, Donghwa Choe, Hojun Kim, Doohyun Baek, Hyeongboo Kang, Brent ByungHoon |
| contents | Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN partitioning (TSDP) mitigates this by isolating sensitive computations, existing paradigms fail to simultaneously satisfy privacy and efficiency. The training-before-partition paradigm suffers from intrinsic privacy leakage, whereas the partition-before-training paradigm incurs severe latency due to structural dependencies that hinder parallel execution. To overcome these limitations, we propose SPOILER, a novel search-before-training framework that fundamentally decouples the TEE sub-network from the backbone via hardware-aware neural architecture search (NAS). SPOILER identifies a lightweight TEE architecture strictly optimized for hardware constraints, maximizing parallel efficiency. Furthermore, we introduce self-poisoning learning to enforce logical isolation, rendering the exposed backbone functionally incoherent without the TEE component. Extensive experiments on CNNs and Transformers demonstrate that SPOILER achieves state-of-the-art trade-offs between security, latency, and accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06263 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SPOILER: TEE-Shielded DNN Partitioning of On-Device Secure Inference with Poison Learning Kang, Donghwa Choe, Hojun Kim, Doohyun Baek, Hyeongboo Kang, Brent ByungHoon Cryptography and Security Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN partitioning (TSDP) mitigates this by isolating sensitive computations, existing paradigms fail to simultaneously satisfy privacy and efficiency. The training-before-partition paradigm suffers from intrinsic privacy leakage, whereas the partition-before-training paradigm incurs severe latency due to structural dependencies that hinder parallel execution. To overcome these limitations, we propose SPOILER, a novel search-before-training framework that fundamentally decouples the TEE sub-network from the backbone via hardware-aware neural architecture search (NAS). SPOILER identifies a lightweight TEE architecture strictly optimized for hardware constraints, maximizing parallel efficiency. Furthermore, we introduce self-poisoning learning to enforce logical isolation, rendering the exposed backbone functionally incoherent without the TEE component. Extensive experiments on CNNs and Transformers demonstrate that SPOILER achieves state-of-the-art trade-offs between security, latency, and accuracy. |
| title | SPOILER: TEE-Shielded DNN Partitioning of On-Device Secure Inference with Poison Learning |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2603.06263 |