Metraipolis › archive › dc_06bce2fdd448
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs — arXiv:2609.12448
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12448
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:08:21.410Z
- SHA-256 of the archived text
ca607b4d6ef48bbb8142a6ff989e713fee7d2bc0dbc1f3151902c89cf1a88d3e- Stable URL of this page
https://metraipolis.com/documento/dc_06bce2fdd448
How to cite
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs — arXiv:2609.12448 — arXiv (en), https://arxiv.org/abs/2609.12448 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06bce2fdd448 (Metraipolis archive dc_06bce2fdd448, sha256 ca607b4d6ef48bbb8142a6ff989e713fee7d2bc0dbc1f3151902c89cf1a88d3e)
BibTeX
@misc{dc06bce2fdd448,
title = {GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs — arXiv:2609.12448},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12448},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06bce2fdd448; sha256 ca607b4d6ef48bbb8142a6ff989e713fee7d2bc0dbc1f3151902c89cf1a88d3e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12448. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sensitive attributes such as age, income, and occupation can be inferred from user-generated content by aggregating indirect cues across many ordinary posts. LLM-based profilers can perform this aggregation automatically and with high accuracy, which makes large-scale personal attribute inference a major privacy threat. Existing LLM-based profilers, however, offer limited insight into which specific posts, concepts, and relationships made an inference possible, which is key to targeted privacy mitigation, i.e., redacting or rewriting only the few posts that actually leak an attribute, rather than perturbing entire histories. We introduce GraphProfiler, an auditable LLM-based profiler that represents each user's post history as a source-linked personal knowledge graph where nodes and edges trace back to the originating post and resolves attribute predictions to cited graph records and source texts. GraphProfiler reaches 86.7% attack success rate on the eight-attribute SynthPAI benchmark, within two points of strong text-only baselines, and 84.6% on PANDORA, while citing supporting evidence for over 98% of predictions. Our controlled ablation experiments provide evidence that the cited posts contribute to attack success, as removing them reduces the attack success rate substantially more than removing an equal number of random posts. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.12448 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T03:02:47.539Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).