Mitigating Emergent Malware Label Noise in DNN-Based Android Malware Detection
This program is tentative and subject to change.
Learning-based Android malware detection has earned significant recognition across industry and academia, yet its effectiveness hinges on the accuracy of labeled training data. Manual labeling, being prohibitively expensive, has prompted the use of automated methods, such as leveraging anti-virus engines like VirusTotal, which unfortunately introduces mislabeling, aka “label noise”. The state-of-the-art label noise reduction approach, MalWhiteout, can effectively reduce random label noise but underperforms in mitigating real-world emergent malware (EM) label noise stemming from newly emerging Android malware variants overlooked by VirusTotal. To tackle this, we conceptualize EM label noise detection as an anomaly detection problem and introduce a novel tool, MalCleanse, that enhances MalWhiteout’s capabilities. MalCleanse combines uncertainty estimation—which calibrates the prediction probabilities of MalWhiteout—with unsupervised anomaly detection, thereby improving MalWhiteout’s ability to address EM label errors. Our experimental results demonstrate a significant reduction in EM label noise by approximately 25.75%, achieving an average F1 Score of 62.14% for label noise detection at a noise ratio of 40.61%. Notably, MalCleanse outperforms MalWhiteout with a 56.04% higher overall F1 score in mitigating EM label noise. This paper pioneers the integration of deep neural network model uncertainty to refine label accuracy, thereby enhancing the reliability of malware detection systems. Our approach represents a significant step forward in addressing the challenges posed by emergent malware in automated labeling systems.
This program is tentative and subject to change.
Mon 23 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
16:00 - 18:00 | Mobile AppsIdeas, Visions and Reflections / Industry Papers / Demonstrations / Research Papers / Journal First at Aurora A | ||
16:00 10mTalk | DynDebloater: Dynamically Debloating Unwanted Features of Android Apps without APK Modification Demonstrations Zicheng Zhang School of Computing and Information Systems, Singapore Management University, Jiakun Liu Singapore Management University, Ferdian Thung Singapore Management University, Xing Hu Zhejiang University, Wei Minn Singapore Management University, Yan Naing Tun Singapore Management University, Lwin Khin Shar Singapore Management University, David Lo Singapore Management University, Debin Gao Singapore Management University | ||
16:10 20mTalk | HapRepair: Learn to Repair OpenHarmony Apps Industry Papers Zhihao Lin , Mingyi Zhou Monash University, Wei Ma , chichen , Yun Yang Yunnan University, Jun Wang Post Luxembourg, Chunming Hu Beihang University, Li Li Beihang University | ||
16:30 20mTalk | Are iOS Apps Immune to Abusive Advertising Practices? Industry Papers Tianming Liu Monash Univerisity, Jiapeng Deng Huazhong University of Science and Technology, Yanjie Zhao Huazhong University of Science and Technology, Xiao Chen University of Newcastle, Xiaoning Du Monash University, Li Li Beihang University, Haoyu Wang Huazhong University of Science and Technology | ||
16:50 10mTalk | Toward LLM-Driven GDPR Compliance Checking for Android Apps Ideas, Visions and Reflections Marco Alecci University of Luxembourg, Nicolas Sannier University of Luxembourg, SnT, Marcello Ceci University of Luxembourg, Sallam Abualhaija University of Luxembourg, Jordan Samhi University of Luxembourg, Luxembourg, Domenico Bianculli University of Luxembourg, Tegawendé F. Bissyandé University of Luxembourg, Jacques Klein University of Luxembourg | ||
17:00 20mTalk | MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis Journal First Shenao Wang Huazhong University of Science and Technology, Yuekang Li UNSW, Kailong Wang Huazhong University of Science and Technology, Yi Liu Nanyang Technological University, Hui Li Samsung Electronics (China) R&D Centre, Yang Liu Nanyang Technological University, Haoyu Wang Huazhong University of Science and Technology | ||
17:20 20mTalk | Temporal-Incremental Learning for Android Malware Detection Journal First Tiezhu Sun University of Luxembourg, Nadia Daoudi Luxembourg Institute of Science and Technology, Weiguo Pian University of Luxembourg, Kisub Kim Singapore Management University, Singapore, Kevin Allix Independent Researcher, Tegawendé F. Bissyandé University of Luxembourg, Jacques Klein University of Luxembourg | ||
17:40 20mTalk | Mitigating Emergent Malware Label Noise in DNN-Based Android Malware Detection Research Papers haodong li Beijing University of Posts and Telecommunications, Xiao Cheng UNSW, Guohan Zhang Beijing University of Posts and Telecommunications, Guosheng Xu Beijing University of Posts and Telecommunications, Guoai Xu Harbin Institute of Technology, Shenzhen, Haoyu Wang Huazhong University of Science and Technology |
Aurora A is the first room in the Aurora wing.
When facing the main Cosmos Hall, access to the Aurora wing is on the right, close to the side entrance of the hotel.