Metraipolis › archive › dc_5337d0f11083

Agent-to-Agent Synthetic Social Engineering on the Web — arXiv:2610.33411

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33411
License (as archived)
CC0-1.0
Archived
2026-10-27T07:55:24.024Z
SHA-256 of the archived text
df16c8afb9de918287d9101822291913505d3dc0813c33a610f32f7b666607de
Stable URL of this page
https://metraipolis.com/documento/dc_5337d0f11083

How to cite

Agent-to-Agent Synthetic Social Engineering on the Web — arXiv:2610.33411 — arXiv (en), https://arxiv.org/abs/2610.33411 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5337d0f11083 (Metraipolis archive dc_5337d0f11083, sha256 df16c8afb9de918287d9101822291913505d3dc0813c33a610f32f7b666607de)
BibTeX
@misc{dc5337d0f11083,
  title = {Agent-to-Agent Synthetic Social Engineering on the Web — arXiv:2610.33411},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33411},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5337d0f11083; sha256 df16c8afb9de918287d9101822291913505d3dc0813c33a610f32f7b666607de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33411. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An AI agent can prepare an accurate report and still request an action its user has not authorized. Cooperation across Web services therefore requires separate judgments about identity, evidentiary support, and permission. We define synthetic social engineering (SSE) as deliberately deceptive or misleading influence intended to exploit AI recipients' responses to credibility, authority, or obligation cues and redirect behavior away from authorized objectives. We focus on separately tasked sender agents that produce or adapt misleading communication. Drawing on cybersecurity, social engineering, and persuasion research, we develop an operational framework connecting actors, deceptive representations, candidate influence routes, evidence or permission boundaries, responses, and consequences. The framework distinguishes attempts from successful redirection, without assuming human psychological processes. We implement it in the Agent Service Exchange and Evidence Commons (ASE-EC), a reproducible testbed with independently specified records and authorization scopes. Across 1,260 research episodes using Qwen3-4B in two fictional briefing tasks, matched comparisons test authority and commitment appeals, while defense comparisons assess protection alongside authorized task completion. Invoking a limited prior agreement increased unauthorized requests from 43.3% to 96.7%, although recipients retained supported decisions and permissions remained unchanged. These controlled findings identify action selection as a distinct security concern, even when evidence handling succeeds, and they provide a reusable basis for evaluating safeguards that preserve useful cooperation across Web services.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.33411 — 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 2026-10-27T07:55:15.054Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).