TruVRF：面向机器遗忘的三重粒度验证
TruVRF: Towards Triple-Granularity Verification on Machine Unlearning
AI总结：
针对机器遗忘缺乏可靠验证方法的问题，提出非侵入式三重粒度验证框架TruVRF，通过三项指标检测不同类型不诚信服务器，在多数据集上表现稳健且具备通用性。
摘要：
“被遗忘权”概念引发了人们对机器遗忘日益增长的研究兴趣，但目前缺乏可靠的验证方法，这为不诚信的模型提供者误导数据贡献者创造了可乘之机。传统的侵入式方法（如后门注入）对遗留数据并不可行。为解决这一问题，我们提出了TruVRF，这是一种在类别级、量级和样本级三种粒度下运行的非侵入式遗忘验证框架。TruVRF包含三项遗忘指标（Unlearning-Metrics），用于检测三类不诚信服务器：疏忽型、懒惰型和欺骗型。遗忘指标I（Unlearning-Metric-I）检查类别对齐情况，遗忘指标II（Unlearning-Metric-II）验证样本数量，遗忘指标III（Unlearning-Metric-III）确认特定样本的删除情况。在三个数据集上的评估显示TruVRF性能稳健：指标I和指标III的准确率超过90%，指标II的推理偏差为4.8%至8.2%。TruVRF还在多种条件下，以及与SISA、Amnesiac Unlearning等前沿遗忘框架的适配中展现出通用性和实用性。
英文摘要：
The concept of the right to be forgotten has led to growing interest in machine unlearning, but reliable validation methods are lacking, creating opportunities for dishonest model providers to mislead data contributors. Traditional invasive methods like backdoor injection are not feasible for legacy data. To address this, we introduce TruVRF, a non-invasive unlearning verification framework operating at class-, volume-, and sample-level granularities. TruVRF includes three Unlearning-Metrics designed to detect different types of dishonest servers: Neglecting, Lazy, and Deceiving. Unlearning-Metric-I checks class alignment, Unlearning-Metric-II verifies sample count, and Unlearning-Metric-III confirms specific sample deletion. Evaluations on three datasets show TruVRF's robust performance, with over 90% accuracy for Metrics I and III, and a 4.8% to 8.2% inference deviation for Metric II. TruVRF also demonstrates generalizability and practicality across various conditions and with state-of-the-art unlearning frameworks like SISA and Amnesiac Unlearning.
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。
