logo

Proposing Automatic Dataset Generation System to Support Android Sensitive Data Leakage Detection Systems

HIEN DO
2:04 08/05/2019

Android sensitive information leakage datasets studies are still limited. Specifically, DroidBench dataset contains 120 case studies of which only 3 case studies are used for analyzing inter-application data flow. Therefore, increasing the number of case study of Android sensitive information leakage datasets is necessary to contribute to improving the accuracy of the evaluations of related research studies in the future. Besides this, the creation of datasets for the evaluation of systems for analyzing other components of the Android operating system such as Application Framework, Linux Kernel, ... is also necessary. In this paper, we propose a system that allows creation of test cases to assess sensitive information leakage detection systems on devices which are using Android operating systems. This system allows creating datasets containing case studies that cause sensitive data leakage not only in a chain of applications but also in the Application Framework component. Evaluation results show that the proposed system works stably with case studies which have a large number of application chains up to 1000 applications and 20 inter-application communication channels for each application pair.

TIN LIÊN QUAN
PoFQ: A Blockchain Consensus Protocol for Decentralized Federated Learning-Based Threat Hunting Approach in a Trustless Computing Landscape
An empirical review of the effectiveness of different language processing approaches in Software Code Vulnerability Detection
The advancement of software vulnerability detection tools has accelerated in recent years, yet the prevalence and severity of vulnerabilities continue to escalate, posing significant threats to computer security and information safety. To address this, numerous detection methodologies have been proposed, with machine learning-based approaches demonstrating notable promise. In this paper,...
RAX-ClaMal: Dynamic Android malware classification based on RAX register values
Detecting malware on Android remains a major challenge because malicious apps use sophisticated evasion techniques. This study presents RAX-ClaMal, a novel approach leveraging dynamic analysis of RAX (Register a Extended) register values for Android malware detection. By extracting and examining the RAX register in the data sections from Dalvik Executable...