SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915534450196480 |
|---|---|
| author | Wang, Zeng Shao, Minghao Karn, Rupesh Mankali, Likhitha Bhandari, Jitendra Karri, Ramesh Sinanoglu, Ozgur Shafique, Muhammad Knechtel, Johann |
| author_facet | Wang, Zeng Shao, Minghao Karn, Rupesh Mankali, Likhitha Bhandari, Jitendra Karri, Ramesh Sinanoglu, Ozgur Shafique, Muhammad Knechtel, Johann |
| contents | Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design Wang, Zeng Shao, Minghao Karn, Rupesh Mankali, Likhitha Bhandari, Jitendra Karri, Ramesh Sinanoglu, Ozgur Shafique, Muhammad Knechtel, Johann Machine Learning Artificial Intelligence Cryptography and Security Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design. |
| title | SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2506.02089 |