Metraipolis › archive › dc_b9424180eeff

Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems — arXiv:2608.24069

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24069
License (as archived)
CC0-1.0
Archived
2026-10-18T06:13:58.288Z
SHA-256 of the archived text
ccf0cbc1dc596f9b699fa5df5b0ce66bcc0a693be59162b620fd18351b2b4023
Stable URL of this page
https://metraipolis.com/documento/dc_b9424180eeff

How to cite

Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems — arXiv:2608.24069 — arXiv (en), https://arxiv.org/abs/2608.24069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b9424180eeff (Metraipolis archive dc_b9424180eeff, sha256 ccf0cbc1dc596f9b699fa5df5b0ce66bcc0a693be59162b620fd18351b2b4023)
BibTeX
@misc{dcb9424180eeff,
  title = {Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems — arXiv:2608.24069},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24069},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b9424180eeff; sha256 ccf0cbc1dc596f9b699fa5df5b0ce66bcc0a693be59162b620fd18351b2b4023},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based multi-agent trading systems, in which specialized agents collaborate through structured communication to produce trading decisions, are moving rapidly from research prototypes to live deployments that control real assets. The same inter-agent communication that makes them effective also exposes them: a corrupted signal can propagate to the final decision and translate into realized financial loss. Unlike prior attacks that presume privileged access to system internals, we restrict the adversary to what is practically reachable---the source data and prompts agents consume---yielding a low-barrier, and thus democratized threat model instantiated as role-specific adversaries. We present the first systematic empirical study in the financial domain to characterize how an adversarial signal enters a multi-agent trading system and how far it survives toward the decision. Along the role axis, we decompose a widely-used trading pipeline into four functional roles---Analyst, Researcher, Trader, and Risk Manager---and pair each with an attack matched to its interface. Along the structural axis, we evaluate four communication topologies under data- and agent-level attacks, using the Adversarial Signal Preservation Score (APS) as a post-hoc lens on why some designs are more robust than others. We conduct experiments across five assets, two backbones, and two target directions. A central finding is that no architecture is inherently robust. These findings provide insights for the future design of safer and more robust agentic trading systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE); Cryptography and Security (cs.CR); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.24069 — 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 2026-10-18T06:07:44.730Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).