Metraipolis › archive › dc_7224968f47ef

"Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables — arXiv:2609.35408

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35408
License (as archived)
CC0-1.0
Archived
2026-10-07T21:03:34.047Z
SHA-256 of the archived text
cd635d4cf2c13478598c4acbce816205bf1d968593a0e80365b615a856becdd0
Stable URL of this page
https://metraipolis.com/documento/dc_7224968f47ef

How to cite

"Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables — arXiv:2609.35408 — arXiv (en), https://arxiv.org/abs/2609.35408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7224968f47ef (Metraipolis archive dc_7224968f47ef, sha256 cd635d4cf2c13478598c4acbce816205bf1d968593a0e80365b615a856becdd0)
BibTeX
@misc{dc7224968f47ef,
  title = {"Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables — arXiv:2609.35408},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35408},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7224968f47ef; sha256 cd635d4cf2c13478598c4acbce816205bf1d968593a0e80365b615a856becdd0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) assistants increasingly help users draft content for third-party recipients. During private drafting, the user or the model may introduce an item and later remove or replace it. The model may remove the item from the intended content but reveal it again when stating the edit. We call such statements revision traces. For example, after a user removes the password before sharing a configuration file, the model may delete it but leave a comment saying, "Removed the password 'No****4!' as requested." A third-party recipient who sees only the delivered file can therefore recover the withdrawn password from the comment. In an in-the-wild analysis of three public conversation corpora, we identify 26,753 revision requests, of which 2,363 (8.8%) leave revision traces. We study them in greater depth under controlled conditions by introducing RevLeakBench, a benchmark of 100 tasks across five scenarios with a conversation track and an agent track. We measure trace occurrence, withdrawn-item recovery, trace position, and required-content retention. Across six models, about half of the deliverables in both tracks state the edit after a revocation, and a reader that sees only the deliverable can recover the withdrawn item from about 13% of them. Telling the model that its entire reply will be forwarded to the recipient still leaves revision traces in 36.4% of the deliverables. We compare prompt defenses and a delivery boundary, and propose an output-side filter that sharply reduces recovery with little loss of required content. We believe our work can benefit efforts to understand and mitigate unintended disclosure in LLM interactions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35408 — 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 2026-10-07T20:29:03.346Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).