BID: Broad Incremental for Android Malware Detection
Keywords: Broad learning system, Android malware detection, Incremental learning, Relational structure
Abstract: With the rapid rise of mobile devices, the threat of malware targeting these platforms has escalated significantly. The fast-paced evolution of Android malware and new attack patterns frequently introduce substantial challenges for detection systems. Although many methods have achieved excellent results, they need to be retrained when faced with new attack modes or observation objects, and it is challenging to attain dynamic updates. To address this issue, we propose a novel Broad Incremental Detection (BID) method for real-time Android malware detection. Our method leverages incremental function to achieve dynamic adaptation to the growing variety of malware attacks while maintaining high computational efficiency, benefiting from its lightweight shallow network architecture. We also develop relational structures to capture complex relations and features of history attacks by fine-turning the network's weights unsupervised. Experimental results across three datasets demonstrate that BID achieves superior detection accuracy and computational efficiency compared to state-of-the-art approaches. Our work presents a robust, flexible, and lightweight framework for dynamic Android malware detection.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13813
Loading