# Distilled Large Language Model in Confidential Computing Environment for System-on-Chip Design

arXiv: https://arxiv.org/abs/2507.16226 · HTML: https://mlsanity.com/paper/2507.16226/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 11 of 11)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging](https://mlsanity.com/paper/2401.16448/) (2024)
- [Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments](https://mlsanity.com/paper/1912.03485/) (2019)
- [SPICED: Syntactical Bug and Trojan Pattern Identification in A/MS Circuits using LLM-Enhanced Detection](https://mlsanity.com/paper/2408.16018/) (2024)
- [ThreatLens: LLM-guided Threat Modeling and Test Plan Generation for Hardware Security Verification](https://mlsanity.com/paper/2505.06821/) (2025)
- [MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models](https://mlsanity.com/paper/2505.11963/) (2025)

## Built on by (most cited first, 2 of 2)

- [PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents](https://mlsanity.com/paper/2603.18377/) (2026)
- [The Open-Weight Paradox: Why Restricting Access to AI Models May Undermine the Safety It Seeks to Protect](https://mlsanity.com/paper/2604.17413/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used in circuit design tasks and have typically undergone multiple rounds of training. Both the trained models and their associated training data are considered confidential intellectual property (IP) and must be protected from exposure. Confidential Computing offers a promising solution to protect data and models through Trusted Execution Environments (TEEs). However, existing TEE implementations are not designed to support the resource-intensive nature of LLMs efficiently. In this work, we first present a comprehensive evaluation of the LLMs within a TEE-enabled confidential computing environment, specifically utilizing Intel Trust Domain Extensions (TDX). We constructed experiments on three environments: TEE-based, CPU-only, and CPU-GPU hybrid implementations, and evaluated their performance in terms of tokens per second. Our first observation is that distilled models, i.e., DeepSeek, surpass other models in performance due to their smaller parameters, making them suitable for resource-constrained devices. Also, in the quantized models such as 4-bit quantization (Q4) and 8-bit quantization (Q8), we observed a performance gain of up to 3x compared to FP16 models. Our findings indicate that for fewer parameter sets, such as DeepSeek-r1-1.5B, the TDX implementation outperforms the CPU version in executing computations within a secure environment. We further validate the results using a testbench designed for SoC design tasks. These validations demonstrate the potential of efficiently deploying lightweight LLMs on resource-constrained systems for semiconductor CAD applications.