Metraipolis › archive › dc_aa3e02ea3dae

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection — arXiv:2610.23307

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.23307
License (as archived): CC0-1.0
Archived: 2026-10-19T08:43:13.402Z
SHA-256 of the archived text: 158884945a7693292329ceb6309adf6b98e8c76f524a6d0211451c55f03d666a
Stable URL of this page: https://metraipolis.com/documento/dc_aa3e02ea3dae

How to cite

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection — arXiv:2610.23307 — arXiv (en), https://arxiv.org/abs/2610.23307 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa3e02ea3dae (Metraipolis archive dc_aa3e02ea3dae, sha256 158884945a7693292329ceb6309adf6b98e8c76f524a6d0211451c55f03d666a)

BibTeX

@misc{dcaa3e02ea3dae,
  title = {MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection — arXiv:2610.23307},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23307},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa3e02ea3dae; sha256 158884945a7693292329ceb6309adf6b98e8c76f524a6d0211451c55f03d666a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23307. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop and web settings, its cross-modal properties in mobile ecosystems remain poorly understood, and existing security analyses are still limited. To close this gap, we introduce MobileInject, the first benchmark for evaluating mobile agents against multimodal injection attacks and reasoning-to-action security risks. MobileInject provides a high-fidelity interactive mobile evaluation framework covering 11 scenarios, 9 security-risk categories, and 108 executable risk instances. It further introduces Cross-Modal Consistency Injection to exploit corroboration across modalities, two enhanced attack methods, Multi-Role Collaborative Deception and Reasoning-Camouflage Injection, to intensify trust manipulation and reasoning hijacking, and a Reasoning Security Diagnosis Framework for fine-grained failure analysis. Systematic experiments show that mobile agents are broadly vulnerable to multimodal injection, and that many failures stem from reasoning hijacking at early stages. These findings establish MobileInject as a systematic cross-modal benchmark for studying and improving the security of mobile agents. Code release details are provided in the Appendix Open Science section.

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/2610.23307 — 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 2026-10-19T08:39:10.153Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).