🛰️ Daily AI Frontier
‹ back to 2026-08-05

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

Research LLM Agents

Ranking

Overall 82
Content 95
Popularity 50

Observed public metrics from 1 member.

Merged summary

TL;DR - AntiSkillBench evaluates privacy leakage and impersonation risks when agents distill personal interaction histories into reusable persona skills. Results show persistent risks across agent backbones and weak generalization from existing defenses.

  • Includes 7,500 persona-grounded dialogue traces from 50 behaviorally rich profiles.
  • Measures attribute disclosure and impersonation of communication styles and personality traits across three skill-distillation strategies.
  • Tests four online and post-hoc defense configurations, including risk suppression and provenance protection.
  • Defense effectiveness varies by distillation method and does not generalize reliably across risks.

Sources (1)

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

arXiv cs.CR Yongli Xiang, Zhifang Zhang, Bojun Yang, Ziming Hong, Lei Feng, Miao Xu, Tongliang Liu 2026-08-04 arXiv:2608.03700
Public signals Hugging Face upvotes 9
Providers: Hugging Face · Upvotes 9 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-03 14:32:53.780388 UTC

TL;DR - AntiSkillBench evaluates privacy leakage and impersonation risks when agents distill personal interaction histories into reusable persona skills. Results show persistent risks across agent backbones and weak generalization from existing defenses.

  • Includes 7,500 persona-grounded dialogue traces from 50 behaviorally rich profiles.
  • Measures attribute disclosure and impersonation of communication styles and personality traits across three skill-distillation strategies.
  • Tests four online and post-hoc defense configurations, including risk suppression and provenance protection.
  • Defense effectiveness varies by distillation method and does not generalize reliably across risks.
item →