Metraipolis › archive › dc_69babe4d14ed

Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting — arXiv:2610.26946

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.26946
License (as archived)
CC0-1.0
Archived
2026-10-21T07:12:33.266Z
SHA-256 of the archived text
2b2ac7a42614e7c86a2139df5a47bbc2301e696ffc3127b3e03f840187879382
Stable URL of this page
https://metraipolis.com/documento/dc_69babe4d14ed

How to cite

Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting — arXiv:2610.26946 — arXiv (en), https://arxiv.org/abs/2610.26946 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69babe4d14ed (Metraipolis archive dc_69babe4d14ed, sha256 2b2ac7a42614e7c86a2139df5a47bbc2301e696ffc3127b3e03f840187879382)
BibTeX
@misc{dc69babe4d14ed,
  title = {Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting — arXiv:2610.26946},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.26946},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69babe4d14ed; sha256 2b2ac7a42614e7c86a2139df5a47bbc2301e696ffc3127b3e03f840187879382},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26946. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models can assist forensic report drafting, but fluent output does not ensure evidentiary reliability. This study presents an evidence-grounded framework for evaluating LLM-assisted Android forensic reports at the atomic-claim level. Gemini, Llama, and Qwen each generated reports for two controlled cases: a public Android 13 dataset and a physical LG device with a zero-reportable-fact boundary. The six accepted reports were decomposed into 612 claims and evaluated against frozen, human-reviewed authorities through content labeling, citation validation, fact-recall analysis, independent rechecking, and dispute resolution. The final corpus contained 424 supported, 163 unsupported, four contradicted, four overstated or incomplete, and 17 excluded claims. In the public case, all three models recovered all 27 authorized report-level facts. Citation validity nevertheless differed substantially: Gemini produced 168 valid citations from 189 required citations, Qwen produced 145 from 189, and Llama produced none from 135. In the physical device case, the models generated 65 claims despite the zero reportable-fact boundary, including 38 unsupported and one contradicted claim. These results show that evidence restriction and complete fact recall do not guarantee claim support or valid evidence attribution. The framework provides an auditable method for detecting unsupported content, preserving claim-to evidence lineage, and retaining investigator authority over final forensic reports.

Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.CY, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.26946 — 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 2026-10-21T07:07:13.790Z dalla pagina https://arxiv.org/list/cs.CY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).