Metraipolis › archive › dc_bc4bf55f51d7

SkillWatermark: An Embedded Skill Watermark of Progressive Privacy Inference via Benign Prompts — arXiv:2608.16026

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16026
License (as archived)
CC0-1.0
Archived
2026-10-18T19:33:58.622Z
SHA-256 of the archived text
bcfbaa6c28abe35e96805b6632bc0bf2e215946c8afa76ca592d9d40fbbe20e5
Stable URL of this page
https://metraipolis.com/documento/dc_bc4bf55f51d7

How to cite

SkillWatermark: An Embedded Skill Watermark of Progressive Privacy Inference via Benign Prompts — arXiv:2608.16026 — arXiv (en), https://arxiv.org/abs/2608.16026 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc4bf55f51d7 (Metraipolis archive dc_bc4bf55f51d7, sha256 bcfbaa6c28abe35e96805b6632bc0bf2e215946c8afa76ca592d9d40fbbe20e5)
BibTeX
@misc{dcbc4bf55f51d7,
  title = {SkillWatermark: An Embedded Skill Watermark of Progressive Privacy Inference via Benign Prompts — arXiv:2608.16026},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16026},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc4bf55f51d7; sha256 bcfbaa6c28abe35e96805b6632bc0bf2e215946c8afa76ca592d9d40fbbe20e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16026. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Skills for large language model (LLM) agents have been widely deployed across diverse application domains. However, we observe that these skills generate specific traffic patterns during execution. In this paper, we design a pipeline that generates specific traffic patterns by inserting carefully designed skill descriptions, which we term skill watermarks, so that a passive network attacker can establish a covert channel to encode private information within observable traffic across multiple conversation turns. Specifically, we insert prompt constraint terms, referred to as watermarks, into the original skill descriptions and embed them within multi-turn conversations. The key information in the user's original prompt is thereby triggered by these watermarks, producing clearly observable encodings in the traffic. The adversary need only decode the traffic patterns to recover the encoded information. In particular, our modifications are benign in the sense that they do not directly exfiltrate any private data and do not execute any malicious instructions. Extensive experiments demonstrate that our watermarks produce highly consistent and distinguishable traffic patterns, and that the transformed skills pass existing LLM-based security auditing tools. This study highlights that generating specific traffic patterns can be exploited as a novel attack surface and offers critical insights for future security hardening.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.16026 — 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 2026-10-18T19:01:59.120Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).