Beijing University of Technology

About: Beijing University of Technology is a education organization based out in Beijing, Beijing, China. It is known for research contribution in the topics: Microstructure & Computer science. The organization has 31929 authors who have published 31987 publications receiving 352112 citations. The organization is also known as: Běijīng Gōngyè Dàxué & Beijing Polytechnic University.

An Explainable Machine Learning Framework for Intrusion Detection Systems

Abstract: In recent years, machine learning-based intrusion detection systems (IDSs) have proven to be effective; especially, deep neural networks improve the detection rates of intrusion detection models. However, as models become more and more complex, people can hardly get the explanations behind their decisions. At the same time, most of the works about model interpretation focuses on other fields like computer vision, natural language processing, and biology. This leads to the fact that in practical use, cybersecurity experts can hardly optimize their decisions according to the judgments of the model. To solve these issues, a framework is proposed in this paper to give an explanation for IDSs. This framework uses SHapley Additive exPlanations (SHAP), and combines local and global explanations to improve the interpretation of IDSs. The local explanations give the reasons why the model makes certain decisions on the specific input. The global explanations give the important features extracted from IDSs, present the relationships between the feature values and different types of attacks. At the same time, the interpretations between two different classifiers, one-vs-all classifier and multiclass classifier, are compared. NSL-KDD dataset is used to test the feasibility of the framework. The framework proposed in this paper leads to improve the transparency of any IDS, and helps the cybersecurity staff have a better understanding of IDSs' judgments. Furthermore, the different interpretations between different kinds of classifiers can also help security experts better design the structures of the IDSs. More importantly, this work is unique in the intrusion detection field, presenting the first use of the SHAP method to give explanations for IDSs.

Diverse manifestations of the mid-Pleistocene climate transition.

Abstract: The mid-Pleistocene transition (MPT) is widely recognized as a shift in paleoclimatic periodicity from 41- to 100-kyr cycles, which largely reflects integrated changes in global ice volume, sea level, and ocean temperature from the marine realm. However, much less is known about monsoon-induced terrestrial vegetation change across the MPT. Here, on the basis of a 1.7-million-year δ13C record of loess carbonates from the Chinese Loess Plateau, we document a unique MPT reflecting terrestrial vegetation changes from a dominant 23-kyr periodicity before 1.2 Ma to combined 100, 41, and 23-kyr cycles after 0.7 Ma, very different from the conventional MPT characteristics. Model simulations further reveal that the MPT transition likely reflects decreased sensitivity of monsoonal hydroclimate to insolation forcing as the Northern Hemisphere became increasingly glaciated through the MPT. Our proxy-model comparison suggests varied responses of temperature and precipitation to astronomical forcing under different ice/CO2 boundary conditions, which greatly improves our understanding of monsoon variability and dynamics from the natural past to the anthropogenic future. The mid-Pleistocene transition is recognized as a shift in paleoclimatic periodicity from 41- to 100-kyr cycles. Here the authors present a unique mid-Pleistocene transition of coupled monsoon-vegetation changes from 23- to 100-kyr cycles, which indicates varied sensitivity of past climate to astronomical and ice/CO2 forcing.

Improving Physical Layer Security via a UAV Friendly Jammer for Unknown Eavesdropper Location

Abstract: In this correspondence paper, we consider an unmanned aerial vehicle (UAV) equipped with an air-to-ground friendly jammer assisting secure communications between a legitimate transmitter–receiver pair for unknown eavesdropper location To enhance the reliability and security of this system, we examine the impact of the UAV jamming power and its three-dimensional (3-D) spatial deployment on the outage probability (OP) of the legitimate receiver and the intercept probability (IP) of the eavesdropper Based on the IP, we develop a new security measure, which we refer to as the intercept probability security region (IPSR) The IPSR defines the region within a target area where the IP is less than a given threshold We design a low-complexity iterative algorithm to maximize the IPSR subject to an OP constraint by jointly optimizing the 3-D deployment and jamming power of the UAV jammer Numerical results show that our proposed iterative algorithm performs close to an exhaustive search with significantly reduced complexity