SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation
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_ | 1866913075331858432 |
|---|---|
| author | Rezakhani, Mahshid Mashnoor, Nowfel Azar, Kimia Kamali, Hadi |
| author_facet | Rezakhani, Mahshid Mashnoor, Nowfel Azar, Kimia Kamali, Hadi |
| contents | As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently lack security verification and are highly susceptible to data poisoning attacks. Such poisoning can cause models to generate syntactically valid but insecure hardware modules that bypass standard functionality checks. To address this, we present SafeTune, a framework designed to harden LLM-based RTL generation against poisoning, specifically focusing on hardware Trojan (HT) insertion. SafeTune integrates two core components: (i) a Graph Neural Network (GNN) that models structural properties to identify anomalous circuitry patterns during fine-tuning, and (ii) a semantic verification module using text embeddings and an XGBoost classifier to assess prompt security. By coupling structural and semantic knowledge, SafeTune effectively filters poisoned inputs without sacrificing legitimate data. Experimental results demonstrate that SafeTune significantly enhances the robustness and reliability of LLM fine-tuning without requiring modifications to the underlying model architecture. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27238 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation Rezakhani, Mahshid Mashnoor, Nowfel Azar, Kimia Kamali, Hadi Cryptography and Security Hardware Architecture As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently lack security verification and are highly susceptible to data poisoning attacks. Such poisoning can cause models to generate syntactically valid but insecure hardware modules that bypass standard functionality checks. To address this, we present SafeTune, a framework designed to harden LLM-based RTL generation against poisoning, specifically focusing on hardware Trojan (HT) insertion. SafeTune integrates two core components: (i) a Graph Neural Network (GNN) that models structural properties to identify anomalous circuitry patterns during fine-tuning, and (ii) a semantic verification module using text embeddings and an XGBoost classifier to assess prompt security. By coupling structural and semantic knowledge, SafeTune effectively filters poisoned inputs without sacrificing legitimate data. Experimental results demonstrate that SafeTune significantly enhances the robustness and reliability of LLM fine-tuning without requiring modifications to the underlying model architecture. |
| title | SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation |
| topic | Cryptography and Security Hardware Architecture |
| url | https://arxiv.org/abs/2604.27238 |