# TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation

arXiv: https://arxiv.org/abs/2503.12217 · HTML: https://mlsanity.com/paper/2503.12217/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 15 Mar 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://mlsanity.com/paper/2109.04332/) (2021)
- [Benchmarking Large Language Models for Automated Verilog RTL Code Generation](https://mlsanity.com/paper/2212.11140/) (2022)
- [BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models](https://mlsanity.com/paper/2406.00083/) (2024)
- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot](https://mlsanity.com/paper/2302.00438/) (2023)
- [AutoQ: Automated Kernel-Wise Neural Network Quantization](https://mlsanity.com/paper/1902.05690/) (2019)
- [FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System](https://mlsanity.com/paper/2303.10837/) (2023)
- [SHE: A Fast and Accurate Deep Neural Network for Encrypted Data](https://mlsanity.com/paper/1906.00148/) (2019)
- [TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models](https://mlsanity.com/paper/2306.06815/) (2023)
- [Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data](https://mlsanity.com/paper/1911.07101/) (2019)
- [HLSPilot: LLM-based High-Level Synthesis](https://mlsanity.com/paper/2408.06810/) (2024)
- [HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture](https://mlsanity.com/paper/2106.00038/) (2021)
- [Primer: Fast Private Transformer Inference on Encrypted Data](https://mlsanity.com/paper/2303.13679/) (2023)
- [CipherPrune: Efficient and Scalable Private Transformer Inference](https://mlsanity.com/paper/2502.16782/) (2025)
- [Are LLMs Any Good for High-Level Synthesis?](https://mlsanity.com/paper/2408.10428/) (2024)
- [Audit and Improve Robustness of Private Neural Networks on Encrypted Data](https://mlsanity.com/paper/2209.09996/) (2022)
- [BoostCom: Towards Efficient Universal Fully Homomorphic Encryption by Boosting the Word-wise Comparisons](https://mlsanity.com/paper/2407.07308/) (2024)
- [Trinity: A General Purpose FHE Accelerator](https://mlsanity.com/paper/2410.13405/) (2024)

## Built on by (most cited first, 4 of 4)

- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [DictPFL: Efficient and Private Federated Learning on Encrypted Gradients](https://mlsanity.com/paper/2510.21086/) (2025)
- [TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code](https://mlsanity.com/paper/2510.11151/) (2025)
- [FHE-Agent: Automating CKKS Configuration for Practical Encrypted Inference via an LLM-Guided Agentic Framework](https://mlsanity.com/paper/2511.18653/) (2025)

## Abstract (arXiv)

Fully Homomorphic Encryption over the torus (TFHE) enables computation on encrypted data without decryption, making it a cornerstone of secure and confidential computing. Despite its potential in privacy preserving machine learning, secure multi party computation, private blockchain transactions, and secure medical diagnostics, its adoption remains limited due to cryptographic complexity and usability challenges. While various TFHE libraries and compilers exist, practical code generation remains a hurdle. We propose a compiler integrated framework to evaluate LLM inference and agentic optimization for TFHE code generation, focusing on logic gates and ReLU activation. Our methodology assesses error rates, compilability, and structural similarity across open and closedsource LLMs. Results highlight significant limitations in off-the-shelf models, while agentic optimizations such as retrieval augmented generation (RAG) and few-shot prompting reduce errors and enhance code fidelity. This work establishes the first benchmark for TFHE code generation, demonstrating how LLMs, when augmented with domain-specific feedback, can bridge the expertise gap in FHE code generation.