English(EN) CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration

新的CertDW方法提供认证数据集所有权验证

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

研究人员开发了CertDW，一种用于验证深度神经网络中数据集所有权的新颖方法。该方法使用一致性校准来确保即使模型受到恶意攻击或扰动时也能进行可靠的验证。CertDW引入了主概率和水印鲁棒性等统计指标来评估模型在良性和带水印样本上的预测稳定性，并提供针对自适应攻击的可证明认证条件。 AI

影响通过提供一种强大的数据集完整性验证方法，增强了AI开发的安全性与可信度。

排序理由该集群包含一篇详细介绍新研究方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新研究方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Ting Qiao, Yiming Li, Jianbin Li, Yingjia Wang, Leyi Qi, Junfeng Guo, Ruili Feng, Dacheng Tao · 2026-09-11 04:00

CertDW：迈向通过共形校准实现的认证数据集所有权验证

arXiv:2506.13160v2 Announce Type: replace Abstract: Deep neural networks (DNNs) rely heavily on high-quality open-source datasets (e.g., ImageNet) for their success, making dataset ownership verification (DOV) crucial for protecting public dataset copyrights. In this paper, we fi…