AI & ML
impact 16
Privacy Leakage via Output Label Space and Differentially Private Continual Learning
Privacy Leakage via Output Label Space and Differentially Private Continual Learning arXiv:2411.04680v5 Announce Type: replace-cross Abstract: Differential privacy (DP) is a formal privacy framework that enables trainin…
Why it matters
The timing matters: privacy is converging with shifts in leakage, which could amplify the downstream impact.