全科医生或专家为您感染的智能手机？
A general practitioner or a specialist for your infected smartphone?
摘要：
随着移动设备数量的爆炸式增长，移动恶意软件也在迅速传播，遇到的恶意软件家族的数量也在增加。现有的解决方案主要基于在手机或云中运行的一个恶意软件检测器，不再有效。主要问题在于，可能不可能创建一个独特的移动恶意软件检测器，该检测器能够以高精度检测不同的恶意软件家族，同时足够轻以不快速消耗电池，并且足够快以及时给出检测结果。所提出的移动恶意软件检测方法类似于处理医疗问题的全科医生与专家方法。类似于全科医生，基于指示性症状识别潜在疾病并将患者发送给适当的专家，我们的检测系统区分代表不同恶意软件家族的症状，一旦检测到症状，它就会触发特定分析。系统监控应用程序的操作方式与全科医生相同。它能够区分不同的症状并触发适当的检测机制。作为对不同专家的类比，使用了一组检测器，其中每个检测器都针对特定的恶意软件家族进行了专门训练。该方法的主要挑战是定义不同恶意软件家族的代表性症状，并相应地对它们进行训练检测器。海报的主要目的是促进对不同恶意软件家族最具代表性的症状的讨论，并讨论通过使用恶意软件基因组项目数据集在这一领域获得的初步结果。
英文摘要：
With explosive growth in the number of mobile devices, the mobile malware is rapidly spreading as well, and the number of encountered malware families is increasing. Existing solutions, which are mainly based on one malware detector running on the phone or in the cloud, are no longer effective. Main problem lies in the fact that it might be impossible to create a unique mobile malware detector that would be able to detect different malware families with high accuracy, being at the same time lightweight enough not to drain battery quickly and fast enough to give results of detection promptly. The proposed approach to mobile malware detection is analogous to general practitioner versus specialist approach to dealing with a medical problem. Similarly to a general practitioner that, based on indicative symptoms identifies potential illnesses and sends the patient to an appropriate specialist, our detection system distinguishes among symptoms representing different malware families and, once the symptoms are detected, it triggers specific analyses. A system monitoring application operates in the same way as a general practitioner. It is able to distinguish between different symptoms and trigger appropriate detection mechanisms. As an analogy to different specialists, an ensemble of detectors, each of which specifically trained for a particular malware family, is used. The main challenge of the approach is to define representative symptoms of different malware families and train detectors accordingly to them. The main goal of the poster is to foster discussion on the most representative symptoms of different malware families and to discuss initial results in this area obtained by using Malware Genome project dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
