跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.09889 · v1

SciCheck: A Framework for Verifying the Integrity of Deep Learning Training

SciCheck:深度学习训练完整性验证框架

首次提交 2026-11-07 02:58
版本更新 2026-11-07 02:58
雷达观测 2026-11-09 13:22
arXiv ↗PDF ↗

摘要

Deep learning training is difficult to verify within a scientific workflow: its architecture, hyperparameters, and procedure are rarely fixed until training has been attempted, and two honest runs never produce the same weights, so recomputation cannot serve as a check. We present SciCheck, a framework in which the scientist explores training configurations freely and posts a blueprint to a provenance ledger for each candidate they want verified, and a verifying scientist judges the resulting run in two layers: a statistical judge model that compares per-step gradient statistics against the verifier's own reference run, and a spot-check that re-executes randomly chosen training segments whose checkpoints are committed to the ledger one epoch at a time. On an MLP, a CNN, and an autoencoder at 100k-500k parameters, under gradient sign flipping, label poisoning, and fabricated runs, SciCheck reaches F1 of 0.966, 0.906, and 0.976 while rejecting 0-4.4% of honest runs. For the attacks we test, the spot-check accounts for most of this accuracy, and we characterize what each layer can detect. The effective-signal statistic falls as (1−2s)2(1-2s)^2 under a sign flip of severity ss, so gradient statistics alone catch strong enough sign flips, while fabricated runs that replay genuine statistics look no more anomalous than honest runs to any statistical detector we test. The spot-check catches fully fabricated segments with probability at least 1−(1−s)k1-(1-s)^k for kk sampled segments when the draws stay hidden until the run is committed, which roughly matches our measurements and lets a verifier choose kk for a target soundness. Verification costs 1.5-2.3x one retraining, mostly for the verifier's reference run; each submission's spot-check takes under 1.5 s, and per-epoch commitments reduce checkpoint storage 5-17x compared with keeping every checkpoint.

作者备注:10 pages, 3 figures, 6 tables

AI 论文解读

基于摘要 · 非全文审阅

提出 SciCheck 框架,用统计判据加随机片段抽查,在溯源账本上验证深度学习训练过程的完整性。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-07 02:58 · 最新观测版本

SciCheck: A Framework for Verifying the Integrity of Deep Learning Training

Deep learning training is difficult to verify within a scientific workflow: its architecture, hyperparameters, and procedure are rarely fixed until training has been attempted, and two honest runs never produce the same weights, so recomputation cannot serve as a check. We present SciCheck, a framework in which the scientist explores training configurations freely and posts a blueprint to a provenance ledger for each candidate they want verified, and a verifying scientist judges the resulting run in two layers: a statistical judge model that compares per-step gradient statistics against the verifier's own reference run, and a spot-check that re-executes randomly chosen training segments whose checkpoints are committed to the ledger one epoch at a time. On an MLP, a CNN, and an autoencoder at 100k-500k parameters, under gradient sign flipping, label poisoning, and fabricated runs, SciCheck reaches F1 of 0.966, 0.906, and 0.976 while rejecting 0-4.4% of honest runs. For the attacks we test, the spot-check accounts for most of this accuracy, and we characterize what each layer can detect. The effective-signal statistic falls as (1−2s)2(1-2s)^2 under a sign flip of severity ss, so gradient statistics alone catch strong enough sign flips, while fabricated runs that replay genuine statistics look no more anomalous than honest runs to any statistical detector we test. The spot-check catches fully fabricated segments with probability at least 1−(1−s)k1-(1-s)^k for kk sampled segments when the draws stay hidden until the run is committed, which roughly matches our measurements and lets a verifier choose kk for a target soundness. Verification costs 1.5-2.3x one retraining, mostly for the verifier's reference run; each submission's spot-check takes under 1.5 s, and per-epoch commitments reduce checkpoint storage 5-17x compared with keeping every checkpoint.

查看此版本解读 →查看此版本原文 ↗