Metraipolis › archive › dc_526dbf63aed6

Pincer: Resource Authorization for Agents using a Digital Twin — arXiv:2610.02569

Source: arXiv
Original: https://arxiv.org/abs/2610.02569
License (as archived): CC0-1.0
Archived: 2026-10-05T22:50:08.425Z
SHA-256 of the archived text: 68d4ea8fce01b256a3156c4e7044670b11fc19413c47326b323d55f58e952a15
Stable URL of this page: https://metraipolis.com/documento/dc_526dbf63aed6

How to cite

Pincer: Resource Authorization for Agents using a Digital Twin — arXiv:2610.02569 — arXiv, https://arxiv.org/abs/2610.02569 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_526dbf63aed6 (Metraipolis archive dc_526dbf63aed6, sha256 68d4ea8fce01b256a3156c4e7044670b11fc19413c47326b323d55f58e952a15)

BibTeX

@misc{dc526dbf63aed6,
  title = {Pincer: Resource Authorization for Agents using a Digital Twin — arXiv:2610.02569},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02569},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_526dbf63aed6; sha256 68d4ea8fce01b256a3156c4e7044670b11fc19413c47326b323d55f58e952a15},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02569. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for self-improvement. While these capabilities have made the agents powerful, they have also made them harder to defend against external adversaries. Defenses that restrict this architecture --- typed tools, information-flow control, or policy prediction engines --- give up too much functionality to be adopted. Agents deployed today (e.g. Claude, Codex) rely on a combination of user-mediated and automode sandboxing as their primary defense. In user-mediated sandboxing, user-maintained policies decay over time and repeated permission requests cause user fatigue, while auto mode's tool-call classifiers learn no user-specific policy and are not meant to defend against adversarial setups. Pincer is a new defense that operates at the resource layer and works alongside existing defenses at the tool-call layer like the auto mode. At the core of Pincer lies a digital twin, an isolated-context model that automatically learns and enforces dynamic user-specific least-privilege policies. The digital twin keeps continually learning the user's preferences allowing it to act as the user's proxy for the agent's permission requests. To emulate the learning phase, we propose a new usercentric dataset with examples following a multi-day transcript of user-agent interaction. Our evaluation shows that Pincer performs strongly on both security and utility in comparison to several baselines which includes variants of LLM judges and adaptations of Conseca (HotOS '25). We highlight attack types where Pincer's design leads to a significant security improvement compared to all other baselines, while outperforming the baselines even for other types of attacks.

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/2610.02569 — 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 2026-10-05T22:45:55.776Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).