Signals 4 · free daily AI digest

Predicting Privacy Leakage from Weight Spectral Density

Paper recorded by Signals 4 on 2026-09-10 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11

Category: cs.LG · 机器学习 · first seen 2026-09-11

Abstract

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 ser

Read on arXiv →

#77 most recent of 215 cs.LG papers we have recorded · ↑ newer: Dynamic language model representations for multi-objective reaction op · ↓ older: Differentially Private EEG Feature Anonymization: A Privacy-Utility Ca
Cite this page: Predicting Privacy Leakage from Weight Spectral Density: the #77 most recent of 215 cs.LG papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/predicting-privacy-leakage-from-weight-spectral-density.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions