arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.14971cs.LG
收藏

细粒度透明机器学习流水线追溯

Fine-Grained Traceability for Transparent ML Pipelines

RMIT University(皇家墨尔本理工大学);Federation University Australia(联邦大学澳大利亚)

Liping Chen, Mujie Liu, Haytham Fayek

AI总结:

FG-Trac是一个模型无关的框架,通过可验证的细粒度样本追溯提升机器学习流水线的透明度和可审计性。

摘要:

现代机器学习系统越来越多地被实现为多阶段流水线,但现有的透明机制通常在模型层面操作:它们描述系统是什么以及为何行为如此,但不跟踪数据样本在流水线中如何被操作、记录和验证。这种缺乏可验证、样本级别的追溯性使从业者和用户无法确定特定样本是否被使用、何时被处理,或相应记录是否在时间上保持完整。我们引入FG-Trac,一个模型无关的框架,该框架在整个机器学习流水线中建立可验证的细粒度样本级别追溯。FG-Trac定义了捕获和验证样本生命周期事件的显式机制,涵盖预处理和训练阶段,计算明确基于训练检查点的贡献分数,并将这些追溯锚定在具有篡改证据的加密承诺上。该框架在不修改模型架构或训练目标的情况下整合,能够以实用的计算开销重建完整的、可审计的数据使用历史。在对一个标准卷积神经网络和多模态图学习流水线的实验中,FG-Trac在保持预测性能的同时,使机器学习系统能够提供可验证的证据,证明个别样本在模型执行过程中是如何被使用和传播的。

英文摘要:

Modern machine learning systems are increasingly realised as multistage pipelines, yet existing transparency mechanisms typically operate at a model level: they describe what a system is and why it behaves as it does, but not how individual data samples are operationally recorded, tracked, and verified as they traverse the pipeline. This absence of verifiable, sample-level traceability leaves practitioners and users unable to determine whether a specific sample was used, when it was processed, or whether the corresponding records remain intact over time. We introduce FG-Trac, a model-agnostic framework that establishes verifiable, fine-grained sample-level traceability throughout machine learning pipelines. FG-Trac defines an explicit mechanism for capturing and verifying sample lifecycle events across preprocessing and training, computes contribution scores explicitly grounded in training checkpoints, and anchors these traces to tamper-evident cryptographic commitments. The framework integrates without modifying model architectures or training objectives, reconstructing complete and auditable data-usage histories with practical computational overhead. Experiments on a canonical convolutional neural network and a multimodal graph learning pipeline demonstrate that FG-Trac preserves predictive performance while enabling machine learning systems to furnish verifiable evidence of how individual samples were used and propagated during model execution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑