Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.12163 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915537483726848 |
|---|---|
| author | Pan, Ruwei Zhang, Hongyu Jiang, Zhonghao Hou, Ran |
| author_facet | Pan, Ruwei Zhang, Hongyu Jiang, Zhonghao Hou, Ran |
| contents | With the increasing prevalence of fraudulent Android applications such as fake and malicious applications, it is crucial to detect them with high accuracy and adaptability. We present AgentDroid, a novel tool for Android fraudulent application detection based on multi-modal analysis and multi-agent systems. AgentDroid overcomes the limitations of traditional detection methods such as the inability to handle multimodal data and high false alarm rates. It processes Android applications and extracts a series of multi-modal data for analysis. Multiple LLM-based agents with specialized roles analyze the relevant data and collaborate to detect complex fraud effectively. We curated a dataset containing various categories of fraudulent applications and legitimate applications and validated our tool on this dataset. Experimental results indicate that our multi-agent tool based on GPT-4o achieves an accuracy of 91.7% and an F1-Score of 91.68%, outperforming the baseline methods. A video of AgentDroid is available at https://youtu.be/YOM9Ex-nBts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12163 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentDroid: A Multi-Agent Framework for Detecting Fraudulent Android Applications Pan, Ruwei Zhang, Hongyu Jiang, Zhonghao Hou, Ran Software Engineering With the increasing prevalence of fraudulent Android applications such as fake and malicious applications, it is crucial to detect them with high accuracy and adaptability. We present AgentDroid, a novel tool for Android fraudulent application detection based on multi-modal analysis and multi-agent systems. AgentDroid overcomes the limitations of traditional detection methods such as the inability to handle multimodal data and high false alarm rates. It processes Android applications and extracts a series of multi-modal data for analysis. Multiple LLM-based agents with specialized roles analyze the relevant data and collaborate to detect complex fraud effectively. We curated a dataset containing various categories of fraudulent applications and legitimate applications and validated our tool on this dataset. Experimental results indicate that our multi-agent tool based on GPT-4o achieves an accuracy of 91.7% and an F1-Score of 91.68%, outperforming the baseline methods. A video of AgentDroid is available at https://youtu.be/YOM9Ex-nBts. |
| title | AgentDroid: A Multi-Agent Framework for Detecting Fraudulent Android Applications |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2503.12163 |