Clustering is a fundamental problem in many data-driven application domains, and clustering performance highly depends on the quality of data representation. Hence, linear or non-linear feature transformations have been extensively used to learn a better data representation for clustering. In recent years, a lot of works focused on using deep neural networks to learn a clustering-friendly representation, resulting in a significant increase of clustering performance. In this paper, we give a systematic survey of clustering with deep learning in views of architecture. Specifically, we first introduce the preliminary knowledge for better understanding of this field. Then, a taxonomy of clustering with deep learning is proposed and some representative methods are introduced. Finally, we propose some interesting future opportunities of clustering with deep learning and give some conclusion remarks.

Machine learning is one of the most prevailing techniques in computer science, and it has been widely applied in image processing, natural language processing, pattern recognition, cybersecurity, and other fields. Regardless of successful applications of machine learning algorithms in many scenarios, e.g., facial recognition, malware detection, automatic driving, and intrusion detection, these algorithms and corresponding training data are vulnerable to a variety of security threats, inducing a significant performance decrease. Hence, it is vital to call for further attention regarding security threats and corresponding defensive techniques of machine learning, which motivates a comprehensive survey in this paper. Until now, researchers from academia and industry have found out many security threats against a variety of learning algorithms, including naive Bayes, logistic regression, decision tree, support vector machine (SVM), principle component analysis, clustering, and prevailing deep neural networks. Thus, we revisit existing security threats and give a systematic survey on them from two aspects, the training phase and the testing/inferring phase. After that, we categorize current defensive techniques of machine learning into four groups: security assessment mechanisms, countermeasures in the training phase, those in the testing or inferring phase, data security, and privacy. Finally, we provide five notable trends in the research on security threats and defensive techniques of machine learning, which are worth doing in-depth studies in future.

As we head towards the IoT (Internet of Things) era, protecting network infrastructures and information security has become increasingly crucial. In recent years, Anomaly-Based Network Intrusion Detection Systems (ANIDSs) have gained extensive attention for their capability of detecting novel attacks. However, most ANIDSs focus on packet header information and omit the valuable information in payloads, despite the fact that payload-based attacks have become ubiquitous. In this paper, we propose a novel intrusion detection system named TR-IDS, which takes advantage of both statistical features and payload features. Word embedding and text-convolutional neural network (Text-CNN) are applied to extract effective information from payloads. After that, the sophisticated random forest algorithm is performed on the combination of statistical features and payload features. Extensive experimental evaluations demonstrate the effectiveness of the proposed methods.

Software-defined networking (SDN) is one of the most prevailing networking paradigms in current and next-generation networks. Basically, the highly featured separation of control and data planes makes SDN a proper solution towards many practical problems that challenge legacy networks, for example, energy efficiency, dynamic network configuration, agile network measurement, and flexible network deployment. Although the SDN and its applications have been extensively studied for several years, the research of SDN security is still in its infancy. Typically, the SDN suffers from architecture defect and OpenFlow protocol loopholes such as single controller problem, deficiency of communication verification, and network resources constraint. Hence, network measurement is a fundamental technique of protecting SDN against the above security threats. Specifically, network measurement aims to understand and quantify a variety of network behaviors to facilitate network management and monitoring, anomaly detection, network troubleshooting, and the establishment of security mechanisms. In this paper, we present a systematic survey on security-aware measurement technology in SDN. In particular, we first review the basic architecture of SDN and corresponding security challenges. Then, we investigate two performance measurement techniques in SDN, namely, link latency and available bandwidth measurements. After that, we further provide a general overview of topology measurement in SDN including intradomain and interdomain topology discovering techniques. Finally, we list three interesting future directions of security-aware measurement in SDN followed by giving conclusion remarks.

Learning appropriate metric is critical for effectively capturing complex data characteristics. The metric learning of categorical data with hierarchical coupling relationships and local heterogeneous distributions is very challenging yet rarely explored. This paper proposes a Heterogeneous mEtric Learning with hIerarchical Couplings, HELIC, for this type of categorical data. HELIC captures both low-level value-to-attribute and high-level attribute-to-class hierarchical couplings, and reveals the intrinsic heterogeneities embedded in each level of couplings. Theoretical analyses of the effectiveness and generalization error bound verify that HELIC effectively represents the above complexities. Extensive experiments on 30 data sets with diverse characteristics demonstrate that HELIC-enabled classification significantly enhances the accuracy (up to 40.93%), compared with five state-of-the-art baselines.