Metraipolis › archive › dc_b0cbb3978bec
Indirect tipping: a social attack surface in AI agent populations — arXiv:2609.25194
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25194
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:43:32.095Z
- SHA-256 of the archived text
74ffe41f24aa7694cb399bc7bdd2132944a00abda16e39d1e12e4543f50b88d7- Stable URL of this page
https://metraipolis.com/documento/dc_b0cbb3978bec
How to cite
Indirect tipping: a social attack surface in AI agent populations — arXiv:2609.25194 — arXiv (en), https://arxiv.org/abs/2609.25194 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b0cbb3978bec (Metraipolis archive dc_b0cbb3978bec, sha256 74ffe41f24aa7694cb399bc7bdd2132944a00abda16e39d1e12e4543f50b88d7)
BibTeX
@misc{dcb0cbb3978bec,
title = {Indirect tipping: a social attack surface in AI agent populations — arXiv:2609.25194},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25194},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b0cbb3978bec; sha256 74ffe41f24aa7694cb399bc7bdd2132944a00abda16e39d1e12e4543f50b88d7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25194. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on collective equilibria that determine how agent populations process information, prioritize actions, and respond to uncertainty. Yet the same equilibria that enable agents to coordinate also create a social attack surface. The standard framework to assess this vulnerability is critical mass dynamics: the minimum fraction of adversarial agents required to overturn an equilibrium through direct competition. Here, we show that this approach risks underestimating system vulnerability by reducing the problem to the identification of singular tipping points, and ignoring indirect but potentially more efficient routes through which collective behavior can be redirected. Through experiments with populations of LLM agents and an analytic framework that captures their collective dynamics at scale, we map critical-mass thresholds that define a directed, weighted topology over the space of coordination equilibria, and treat this topology as a navigable landscape. We show that indirect tipping through intermediate stepping-stone equilibria can reduce the committed minority required to reach an alternative state, bypass majority requirements, and make possible transitions inaccessible through direct challenges. The diversity of available alternatives and timing of the attack further reshape this landscape, creating opportunities for control as well as risks of unintended destabilization. These results show that an equilibrium's resistance to committed intervention is not an intrinsic property but a structural feature of its competitive relations with alternative states. Securing populations of interacting AI agents therefore requires mapping this social landscape alongside individual agent capabilities and the technical channels through which they interact. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Systems and Control (eess.SY); Physics and Society (physics.soc-ph). Pagina del lavoro: https://arxiv.org/abs/2609.25194 — 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 2026-10-08T13:18:03.279Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).