Mobile devices have been and will be continuously prevalent as rich applications are provided for various demands. However, the mobile operating system lacks efficient malware detection tools, which puts personal data at risk. This paper presents MobiPCR, a trict, accurate, efficient mobile-oriented malware detection system. MobiPCR basically integrates a (n) (edge) cloud-based architecture, a powerful yet efficient machine learning-based detection model, and a neat detection process. We implemented the MobiPCR prototype system and conducted rigorous experiments to evaluate its performance from different perspectives. We implemented the MobiPCR prototype system on the Android platform (Installer Hooker part) considering that Android is an open-source platform that (i) can be easily modified and (ii) provides rich documentation. We used LineageOS 13 (a widespread Android distribution) to provide the necessary drivers to support communication and the camera for casual usage. Experimental results prove that MobiPCR can strictly and accurately detect malwares and outperform existing similar applications without extra operations.

Mining feature evolvable streams has gained increasing attention in recent years. However, most existing approaches are designed for stationary data streams (i.e., data streams without concept drifts) and often work with high time complexity due to the time-consuming optimization procedure. The two deficiencies thus largely limit its applications to real-world data stream scenarios. In this paper, we consider a more difficult but practical streaming setting: a data stream with both concept drifts and evolvable features. To this end, we propose a general framework for mining concept-drifting data streams with evolvable features, called FEMC, based on an efficient Feature Evolvable streaming learning and dynamic Micro-Clusters maintenance. Specifically, we derive a closed-form solution to preserve the information in vanished features by learning a weight vector on survival features. The evolving concepts, are further learnt by dynamically maintaining a set of micro-clusters with varying feature space on-the-fly. Empirical results on real-world data sets have demonstrated the benefits of the proposed framework on both clustering and classification tasks by comparing with state-of-the-art algorithms.

Community detection in attributed networks has gained growing attention in recent years due to the booming of network data with both topological structure and attributes of nodes. To date, numerous algorithms have been proposed to leverage both kinds of information to yield high-quality communities based on homophily assumption (i.e., nodes are likely to link with those who share similar attributes). However, these approaches tend to focus on consistent information only and fail to consider the heterogeneity between topology and attributes. In light of the problem, we propose a new algorithm called CDLM (Community Detection via Local Metric learning) for attributed networks. The key point is to combine topological structure and node attributes in local metric space and perform community detection and local metric learning iteratively. With such a strategy, the learned local distance measures will benefit the performance of community detection, and in turn, the identification of intrinsic community structure helps to eliminate the negative effects of noisy edges in learning local metrics. Notably, homogeneity and heterogeneity between topological structure and node attributes are simultaneously considered to boost the performance of community detection. Experimental results on both synthetic and real-world networks have demonstrated the effectiveness of the proposed CDLM algorithm.

This paper focuses on traffic sign spotting (TSS which automatically recognizes not only the conventional traffic signs but also information, facility and service signs, and traffic lights. TSS is divided into two sequential tasks: detecting traffic sign candidate regions in an image and recognizing the traffic signs in the regions. It is a very challenging task. We make the following contributions: 1) we create a traffic sign collection from the driverless car. The traffic signs are shot under the natural environment which covers large variation in illuminance and weather conditions. It not only contains the common traffic signs but also contains the information, facility and service signs which are called signposts, as well as traffic lights. 2) we proposed a systematic solution. We construct an Inception convolutional neural network. We use Faster-RCNN for traffic sign detection and make it suitable to detect small targets. 3) We adopt three schemes for the common traffic signs, the signposts and the traffic lights, respectively. The experimental results demonstrate the effectiveness and efficiency of our methods. Our methods won the first place in the traffic sign recognition task of Intelligent Vehicle Future Challenge 2017, China.