Toward Hardware Security Benchmarking of LLMs
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
With the rapid advancement and proliferation of large language models (LLMs), there is a pressing need to explore and, crucially, evaluate their utility. Recently, LLMs have shown promise in digital design, with evidence of some ability to produce functional HDL code. However, to better understand LLM capabilities and guide the ongoing development of LLMs, we need approaches to evaluate the quality of generated artifacts across myriad dimensions. Thus, this work proposes an approach for evaluating the security of LLM-generated designs, which is especially important as security is an ongoing concern. We provide new insights into the challenges and desiderata for benchmarking LLMs for hardware security risks. This paper outlines our initial work developing a security-focused evaluation suite for LLM-aided HDL generation. We present an illustrative preliminary use of our evaluation suite to show the insights we can gain from security evaluation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it