MétaCan
Menu
Back to cohort

Toward Hardware Security Benchmarking of LLMs

2024· article· en· W4403024154 on OpenAlexafffund
Raheel Afsharmazayejani, Mohammad Moradi Shahmiri, Parker Link, Hammond Pearce, Benjamin Tan

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSecurity and Verification in Computing
Canadian institutionsUniversity of Calgary
FundersNatural Sciences and Engineering Research Council of CanadaIntel Corporation
KeywordsBenchmarkingComputer scienceComputer securityBusiness

Abstract

fetched live from OpenAlex

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.014
metaresearch head score (Gemma)0.055
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.014
Threshold uncertainty score0.072

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.055
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.001

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.

Opus teacher head0.034
GPT teacher head0.274
Teacher spread0.240 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations10
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicSecurity and Verification in ComputingFrench-language works237,207