Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills

First seen · 8/4/2026, 04:00 AMLatest activity · 8/4/2026, 04:00 AM

The paper introduces AntiSkillBench, an end-to-end benchmark for privacy leakage, attribute disclosure, behavioral impersonation, and defenses in persona-skill pipelines. It contains 7,500 persona-grounded dialogue traces built from 50 behaviorally rich profiles, evaluates three skill-distillation strategies, and tests four online or post-hoc defense configurations. Experiments across three frontier agents suggest that risks persist across backbones and distillation protocols, extending beyond explicit attributes to communication styles and personality traits. Existing defenses show limited and distillation-dependent effectiveness.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers8/4, 04:00 AMnot independentRepresentative
    When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills