Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.16716 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909856387039232 |
|---|---|
| author | Mohanty, Asmita Kang, Gezheng Gao, Lei Annavaram, Murali |
| author_facet | Mohanty, Asmita Kang, Gezheng Gao, Lei Annavaram, Murali |
| contents | Large Language Models (LLMs) have demonstrated strong performance across diverse tasks, but fine-tuning them typically relies on cloud-based, centralized infrastructures. This requires data owners to upload potentially sensitive data to external servers, raising serious privacy concerns. An alternative approach is to fine-tune LLMs directly on edge devices using local data; however, this introduces a new challenge: the model owner must transfer proprietary models to the edge, which risks intellectual property (IP) leakage. To address this dilemma, we propose DistilLock, a TEE-assisted fine-tuning framework that enables privacy-preserving knowledge distillation on the edge. In DistilLock, a proprietary foundation model is executed within a trusted execution environment (TEE) enclave on the data owner's device, acting as a secure black-box teacher. This setup preserves both data privacy and model IP by preventing direct access to model internals. Furthermore, DistilLock employs a model obfuscation mechanism to offload obfuscated weights to untrusted accelerators for efficient knowledge distillation without compromising security. We demonstrate that DistilLock prevents unauthorized knowledge distillation processes and model-stealing attacks while maintaining high computational efficiency, but offering a secure and practical solution for edge-based LLM personalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16716 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge Mohanty, Asmita Kang, Gezheng Gao, Lei Annavaram, Murali Cryptography and Security Machine Learning Large Language Models (LLMs) have demonstrated strong performance across diverse tasks, but fine-tuning them typically relies on cloud-based, centralized infrastructures. This requires data owners to upload potentially sensitive data to external servers, raising serious privacy concerns. An alternative approach is to fine-tune LLMs directly on edge devices using local data; however, this introduces a new challenge: the model owner must transfer proprietary models to the edge, which risks intellectual property (IP) leakage. To address this dilemma, we propose DistilLock, a TEE-assisted fine-tuning framework that enables privacy-preserving knowledge distillation on the edge. In DistilLock, a proprietary foundation model is executed within a trusted execution environment (TEE) enclave on the data owner's device, acting as a secure black-box teacher. This setup preserves both data privacy and model IP by preventing direct access to model internals. Furthermore, DistilLock employs a model obfuscation mechanism to offload obfuscated weights to untrusted accelerators for efficient knowledge distillation without compromising security. We demonstrate that DistilLock prevents unauthorized knowledge distillation processes and model-stealing attacks while maintaining high computational efficiency, but offering a secure and practical solution for edge-based LLM personalization. |
| title | DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2510.16716 |