Tuesday 17 November, Technology & Tools

Why deleting data can fail in agent networks

Why deleting data can fail in agent networks

The study shows deleted data can still echo through later training rounds in self-improving federated agent networks.

Reported by arXiv

Why it matters

It raises the cost and complexity of data deletion in systems that keep learning after launch.

Key facts

  • The paper argues that unlearning gets harder when agents keep training after deployment.
  • If a data owner asks for deletion, the original data may already have shaped later trajectories that are kept.
  • The authors say that influence can survive retraining, grow with more forget-shaped data, and be traced through deployment, collection, and aggregation records.
Petrol todayFill up or wait? Today's call for every capital

Today on InSnip

  1. Man dies in shooting at Belmont Local Court south of NewcastlePower & Policy, 7NEWS, 2 h ago
  2. David Jones suppliers face months of limbo on $419m debtMoney & Work, The Sydney Morning Herald, 2 h ago
  3. One Nation vows Victoria ban on puberty blockers after states reject guidancePower & Policy, SBS News, 5 h ago

Today's ten are ready.

Read today's tenAbout seven minutes, free