Metraipolis › archive › dc_c52186cb0bdf
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use — arXiv:2610.04985
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04985
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:37.126Z
- SHA-256 of the archived text
0e99944be008973ae5d44349b099547ec1e1785b69a6f0c139698056e358641d- Stable URL of this page
https://metraipolis.com/documento/dc_c52186cb0bdf
How to cite
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use — arXiv:2610.04985 — arXiv, https://arxiv.org/abs/2610.04985 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c52186cb0bdf (Metraipolis archive dc_c52186cb0bdf, sha256 0e99944be008973ae5d44349b099547ec1e1785b69a6f0c139698056e358641d)
BibTeX
@misc{dcc52186cb0bdf,
title = {Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use — arXiv:2610.04985},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04985},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c52186cb0bdf; sha256 0e99944be008973ae5d44349b099547ec1e1785b69a6f0c139698056e358641d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04985. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implications of this emerging use remain largely unexplored. To address this gap, we conduct the first systematic study of these implications using the official Jev API and NanoJev, a local model with controllable training data and updates, focusing on three research questions: (1) What security threats arise when Jev is deployed as an application decision layer? (2) What private information can Jev reveal despite returning constrained typed outputs? (3) How can Jev's general-purpose decision capability be used for beneficial purposes or misused? Jev's decisions depend on application state and may be influenced by user-provided inputs. We therefore adapt prompt injection and adversarial suffixes to manipulate its decisions. Open-source Jev distribution and updates introduce supply-chain risks, which we examine by implanting backdoors in NanoJev through training data poisoning. Since Jev's outputs reflect both application state and information learned during training, we further adapt membership, private attribute, and internal knowledge inference attacks to recover sensitive information despite its constrained output format. Finally, Jev can serve as a general-purpose decision oracle for defensive and malicious workflows. We examine this dual use through four detection tasks covering prompt injection, jailbreak inputs, harmful content, and AI-generated text, alongside misuse scenarios involving jailbreak and model extraction. Our empirical evaluation shows that Jev remains vulnerable to the examined security and privacy threats, while its decision capability can support beneficial and malicious uses. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.04985 — 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 2026-10-06T05:24:05.953Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).