Metraipolis › archive › dc_8906307328ee
MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents — arXiv:2610.23303
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23303
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:46:40.132Z
- SHA-256 of the archived text
db1394b6059f6608f1fa9b4d942136dd0dbf62bea0f73eb1da3f42cd1552a572- Stable URL of this page
https://metraipolis.com/documento/dc_8906307328ee
How to cite
MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents — arXiv:2610.23303 — arXiv (en), https://arxiv.org/abs/2610.23303 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8906307328ee (Metraipolis archive dc_8906307328ee, sha256 db1394b6059f6608f1fa9b4d942136dd0dbf62bea0f73eb1da3f42cd1552a572)
BibTeX
@misc{dc8906307328ee,
title = {MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents — arXiv:2610.23303},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23303},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8906307328ee; sha256 db1394b6059f6608f1fa9b4d942136dd0dbf62bea0f73eb1da3f42cd1552a572},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23303. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
MLLM-based mobile agents are rapidly gaining autonomy in perception, planning, and closed-loop execution in dynamic mobile environments. However, this autonomy also broadens the attack surface and amplifies the risks of malicious misuse, including privacy leakage, device compromise, and large-scale phishing. Existing jailbreak evaluations leave three critical gaps for mobile agents: they focus on conversational attacks instead of mobile workflows, use static task sets with fixed difficulty, and rely narrowly on attack success rate rather than comprehensive security assessment. To close these gaps, we present MobileJailBench, the first evolving jailbreak benchmark for mobile agents, comprising three key components: (1) a benchmark comprising 520 tasks spanning three jailbreak paradigms and 14 risk categories, built on a high-fidelity mobile sandbox that we construct, enabling realistic workflows across over 20 widely used apps; (2) Dual-Dynamic Evolution, which combines Failure-Distilled Jailbreak Evolution with Weakness-Driven Benchmark Expansion; and (3) Stratified Adjudication Framework for assessing security awareness, execution behavior, and risk consequences. Extensive experiments show that current mobile agents are particularly vulnerable to implicit jailbreaks, as their safety alignment remains largely superficial and fails to generalize from conversational refusal to dynamic mobile interactions. Moreover, our dynamic evolution mechanism sharpens practical threat boundaries by continually uncovering new vulnerabilities, reaching a 100% ASR on Qwen3.5-122B. MobileJailBench provides a reproducible, continuously evolving framework for tracking the true security boundaries of mobile agents. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2610.23303 — 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 2026-10-19T08:41:54.782Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).