Skill-level leakage is strongest for communication style and personality, not explicit demographics¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Leakage is not limited to explicit demographics; it is strongest for background, personality, and communication style dimensions. → Yongli Xiang 2026
Evidence¶
Yongli Xiang 2026¶
Yongli Xiang, Zhifang Zhang, Bojun Yang, Ziming Hong, Lei Feng, Miao Xu, Tongliang Liu. (2026). When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills. arXiv. https://arxiv.org/abs/2608.03700 doi:10.48550/arxiv.2608.03700
q2 · i? · design · r2
Main evaluation results in Table 1 on GPT 5.4 show communication coverage "stays between 88.0 and 92.0, while personality ranges from 69.0 to 75.7", while demographic coverage is far lower (e.g., 19.2 under three-stage Distill). Values are descriptive percentages with no effect sizes printed.
"Leakage is not limited to explicit demographics; it is strongest for background,personality,andcommunicationstyle.ForGPT 5.4, overall Skill Coverage remains high across protocols, reaching66.2forthree-stage,63.6forDirectDistill,and55.2 for Colleague Distill."
Discussion¶
Related Claims¶
- Active defenses (Privacy Sanitization, Adversarial Obfuscation) reduce but do not eliminate persona-skill leakage, leaving personality and background exposed — related
- Skill-equipped agents reproduce target users' attributes and language, enabling impersonation across unseen contexts — related
- Persona-skill distillation encodes substantial private information into skill artifacts, persisting across agent backbones and distillation protocols — related
- Passive backdoor defense (SBD) effectiveness is distillation-dependent, degrading under persona-centric abstraction — related
- Privacy protection in the framework is partial: three residual leakage channels remain open — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
leakage-strongest-communication-personality |
title |
Skill-level leakage is strongest for communication style and personality, not explicit demographics |
description |
Skill-level leakage is strongest for communication style and personality, not explicit demographics |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
source_checked |
2026-10-20 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yongli-xiang-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.