Predicting Privacy Leakage from Weight Spectral Density
Study shows WeightWatcher spectral metrics like stable rank correlate with membership inference vulnerability, enabling cheaper ML privacy auditing.
The paper tests whether spectral metrics from the heavy-tailed self-regularisation framework can proxy membership inference attack (MIA) vulnerability without training expensive shadow models. On image and tabular classification tasks, stable rank correlates positively with overall MIA success, while Log alpha-Norm correlates negatively at the low false-positive regime. These correlations are stronger than those obtained from the generalisation gap, suggesting weight spectra capture leakage information overfitting measures miss. The authors propose spectral analysis as a scalable direction for privacy auditing.
- Stable rank strongly correlates with overall MIA success
- Log alpha-Norm correlates with vulnerability at low false-positive regime
- Spectral signals outperform the generalisation gap as leakage proxies
- Could reduce reliance on costly shadow-model privacy audits
- Products
- WeightWatcher
From the original article
1 min read at arxiv.orgMembership 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.
By Richard J. Preen · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.