MétaCan
Menu
Back to cohort

Memory-Efficient Differential Privacy Accelerator

2025· article· W7130561410 on OpenAlexaff
Muhammad Hamis Haider, Nam-Joon Kim, Hailong Zhang, Janier Arias-García, Hyuk-Jae Lee, Seok‐Bum Ko

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicPhysical Unclonable Functions (PUFs) and Hardware Security
Canadian institutionsUniversity of Saskatchewan
Fundersnot available
KeywordsScalabilityLeverage (statistics)Noise (video)Overhead (engineering)Entropy (arrow of time)ComputationField-programmable gate arrayGenerator (circuit theory)Differential privacy

Abstract

fetched live from OpenAlex

This paper introduces a memory-efficient accelerator for differentially private machine learning that significantly reduces memory overhead through in-line noise generation and approximate gradient computation. The core of the design is a metastability-driven Gaussian noise generator paired with an approximate computation unit, both implemented on FPGA and modeled in Pytorch extension library. We leverage controlled clock phase mismatches to induce entropy in flip-flop arrays. These metastable outputs are processed through a pipelined Box-Muller transform to produce scalable, high-throughput noise samples at configurable privacy levels. By integrating noise addition into the computational pipeline, the system avoids the traditional need for separate noise sampling and post-processing stages, reducing per-epoch memory operations by up to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 2. 5 \%}$</tex> in simulation and a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 6 \%}$</tex> improvement in throughput of the accelerator. The proposed approach offers a scalable and practical solution for hardware-accelerated private learning with strict memory and power constraints.

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 distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.882
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.002
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0020.003
Research integrity0.0000.001
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 head0.014
GPT teacher head0.254
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; both teacher heads agree on what is shown here.

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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicPhysical Unclonable Functions (PUFs) and Hardware SecurityFrench-language works237,207