Metraipolis › archive › dc_43489cfebc44

Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents — arXiv:2609.18357

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18357
License (as archived)
CC0-1.0
Archived
2026-10-15T13:49:56.541Z
SHA-256 of the archived text
da89bcc7d62822e2ec92f28b97b14453db058cae4f8424276a314480fff551e9
Stable URL of this page
https://metraipolis.com/documento/dc_43489cfebc44

How to cite

Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents — arXiv:2609.18357 — arXiv (en), https://arxiv.org/abs/2609.18357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43489cfebc44 (Metraipolis archive dc_43489cfebc44, sha256 da89bcc7d62822e2ec92f28b97b14453db058cae4f8424276a314480fff551e9)
BibTeX
@misc{dc43489cfebc44,
  title = {Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents — arXiv:2609.18357},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18357},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43489cfebc44; sha256 da89bcc7d62822e2ec92f28b97b14453db058cae4f8424276a314480fff551e9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) pricing agents may respond to how market data is presented, even when its numerical values remain unchanged. We introduce market signal injection (MSI), an attack that manipulates numerical formatting, competitor ordering, or qualitative market commentary without issuing explicit instructions. We evaluate nine open-weight models in simulated Bertrand duopoly and triopoly markets and three proprietary models in duopoly markets. Sentiment-based attacks produce the largest behavioral shifts, which propagate to other firms and alter profits and consumer surplus. Susceptibility varies across model families, and larger models are not consistently more robust. Matched neutral-text controls and a rule-based agent support a framing-based account of these shifts under the fixed demand parameters of our simulation. Episode-held-out probes distinguish baseline from attacked activations in all eleven re-evaluated model--condition pairs: linear AUC is 1.00 and MLP AUC ranges from 0.93 to 0.99. This separability does not by itself identify harmful pricing decisions. Input canonicalization removes the tested sentiment attacks, while decision boundary anchoring, which combines prompt constraints with output projection, provides partial mitigation under the tested adaptive attacks. These results identify data presentation as an attack surface for LLM pricing agents and motivate defenses that account for interactions among agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.18357 — 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 2026-10-15T13:48:24.418Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).