Security — recent AI signals

Signals we've tagged as "security" across our sources, newest first.

• Sep 10, 2026 arxiv
  Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
  Cardiovascular screening models trained on national health surveys routinely report areas under the receiver operating characteristic curve (AUROC) near 0.89. We asked whether that
• Sep 10, 2026 compass
  Nvidia’s Huang Touts Cybersecurity as Next Big Market for AI - Bloomberg.com
  Nvidia’s Huang Touts Cybersecurity as Next Big Market for AI - Bloomberg.com
• Sep 10, 2026 arxiv
  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 compu