研究用权重谱密度预测模型隐私泄露风险
Predicting Privacy Leakage from Weight Spectral Density
这是篇挺有意思的论文，作者发现用模型权重谱的几个数学指标就能大概判断模型会不会被用来偷用户数据，比传统方法更高效。
这项研究提出了一种新方法，通过分析神经网络权重谱的特定指标（如稳定秩和Log alpha-Norm）来评估模型被用于成员推断攻击（MIA）的风险。在图像和表格分类任务上，这些光谱指标与MIA的成功率有更强的相关性，比传统的泛化差距指标更有效。
Predicting Privacy Leakage from Weight Spectral Density
Membership inference attacks (MIAs) are widely used to audit the privacy disclosure risk of machine learning models, however current state-of-the-art attacks require training computationally expensive shadow models, making large-scale privacy evaluation impractical. In this work, we investigate whether inexpensive spectral metrics derived from the heavy-tailed self-regularisation framework can serve as proxies for MIA vulnerability. We evaluate several WeightWatcher spectral metrics on image and tabular classification tasks and compare their relationship with MIA privacy leakage against conventional measures of generalisation. Across datasets, stable rank exhibits a strong positive correlation with overall MIA success, while Log alpha-Norm shows a consistent negative correlation with MIA vulnerability at the low false-positive regime. These associations are observed to be stronger than those obtained using the generalisation gap. The results indicate that neural network spectra may contain information about privacy leakage that is not fully captured by conventional measures of overfitting, motivating spectral analysis as a promising direction for scalable privacy auditing.