SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908429475381248 |
|---|---|
| author | Liang, Siyuan Fang, Tianmeng Liu, Zhe Liu, Aishan Xiao, Yan He, Jinyuan Chang, Ee-Chien Cao, Xiaochun |
| author_facet | Liang, Siyuan Fang, Tianmeng Liu, Zhe Liu, Aishan Xiao, Yan He, Jinyuan Chang, Ee-Chien Cao, Xiaochun |
| contents | With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large model-driven agents. However, the related systems are also increasingly exposed to potential jailbreak risks. Attackers may induce the agents to bypass the original behavioral constraints through specific inputs, and then trigger certain risky and sensitive operations, such as modifying settings, executing unauthorized commands, or impersonating user identities, which brings new challenges to system security. Existing security measures for intelligent agents still have limitations when facing complex interactions, especially in detecting potentially risky behaviors across multiple rounds of conversations or sequences of tasks. In addition, an efficient and consistent automated methodology to assist in assessing and determining the impact of such risks is currently lacking. This work explores the security issues surrounding mobile multimodal agents, attempts to construct a risk discrimination mechanism by incorporating behavioral sequence information, and designs an automated assisted assessment scheme based on a large language model. Through preliminary validation in several representative high-risk tasks, the results show that the method can improve the recognition of risky behaviors to some extent and assist in reducing the probability of agents being jailbroken. We hope that this study can provide some valuable references for the security risk modeling and protection of multimodal intelligent agent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00841 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents Liang, Siyuan Fang, Tianmeng Liu, Zhe Liu, Aishan Xiao, Yan He, Jinyuan Chang, Ee-Chien Cao, Xiaochun Artificial Intelligence Cryptography and Security With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large model-driven agents. However, the related systems are also increasingly exposed to potential jailbreak risks. Attackers may induce the agents to bypass the original behavioral constraints through specific inputs, and then trigger certain risky and sensitive operations, such as modifying settings, executing unauthorized commands, or impersonating user identities, which brings new challenges to system security. Existing security measures for intelligent agents still have limitations when facing complex interactions, especially in detecting potentially risky behaviors across multiple rounds of conversations or sequences of tasks. In addition, an efficient and consistent automated methodology to assist in assessing and determining the impact of such risks is currently lacking. This work explores the security issues surrounding mobile multimodal agents, attempts to construct a risk discrimination mechanism by incorporating behavioral sequence information, and designs an automated assisted assessment scheme based on a large language model. Through preliminary validation in several representative high-risk tasks, the results show that the method can improve the recognition of risky behaviors to some extent and assist in reducing the probability of agents being jailbroken. We hope that this study can provide some valuable references for the security risk modeling and protection of multimodal intelligent agent systems. |
| title | SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2507.00841 |