用户可用小样本标记，检测模型是否未经许可使用其数据。
Anonymity Unveiled: A Practical Framework for Auditing Data Use in Deep Learning Models
- 用微小改动标记数据，让模型容易记住目标样本。
- 仅需0.005%~0.1%的数据标记量，即可实现零误报率的检测。
- 适合关注数据隐私的普通用户和合规审计人员。
深度学习模型训练对数据需求激增，导致大量用户数据（如人脸图像）在未经同意的情况下被采集使用，引发严重隐私担忧。本文提出MembershipTracker，一种实用的数据审计工具，帮助普通用户可靠检测其数据是否被用于模型训练。该方法从成员推断（MI）视角出发，通过轻量级数据标记组件对目标数据施加微小但有针对性的修改，使其易被模型记忆；再结合专用的MI验证流程，判断模型是否对这些标记样本存在强记忆。实验表明，该方法仅需标记训练集0.005%至0.1%的数据，即可在全尺寸ImageNet-1k等工业级训练场景下实现平均0%误报率（FPR@100% TPR）的精准检测，并在多种对抗措施下仍保持高效。结果证明其具备广泛适用性和实用性。
原文摘要 · Abstract (English)
The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Meanwhile, users often have limited control over whether their data (e.g., facial images) are used to train DL models without their consent, which has engendered pressing concerns. This work proposes MembershipTracker, a practical data auditing tool that can empower ordinary users to reliably detect the unauthorized use of their data in training DL models. We view data auditing through the lens of membership inference (MI). MembershipTracker consists of a lightweight data marking component to mark the target data with small and targeted changes, which can be strongly memorized by the model trained on them; and a specialized MI-based verification process to audit whether the model exhibits strong memorization on the target samples. MembershipTracker only requires the users to mark a small fraction of data (0.005% to 0.1% in proportion to the training set), and it enables the users to reliably detect the unauthorized use of their data (average 0% FPR@100% TPR). We show that MembershipTracker is highly effective across various settings, including industry-scale training on the full-size ImageNet-1k dataset. We finally evaluate MembershipTracker under multiple classes of countermeasures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。