Android malware severely threaten system and user security in terms of privilege escalation, remote control, tariff theft, and privacy leakage. Therefore, it is of great importance and necessity to detect Android malware. In this paper, we present a combination method for Android malware detection based on the machine learning algorithm. First, we construct the control flow graph of the application to obtain API information. Based on the API information, we innovatively construct Boolean, frequency, and time-series data sets. Based on these three data sets, three detection models for Android malware detection regarding API calls, API frequency, and API sequence aspects are constructed. Ultimately, an ensemble model is constructed for conformity. We tested and compared the accuracy and stability of our detection models through a large number of experiments. The experiments were conducted on 10010 benign applications and 10683 malicious applications. The results show that our detection model achieves 98.98% detection precision and has high accuracy and stability. All of the results are consistent with the theoretical analysis in this paper. INDEX TERMS Control flow graph, application programming interface, machine learning, malware detection.
In order to solve the problem of slow convergence speed and long planned path when the robot plans a path in unknown environment by using Q-learning algorithm, we propose the Experience-Memory Q-Learning (EMQL) algorithm based on the continuous update of the shortest distance from the current state node to the start point. The autonomous learning ability of the robot is enhanced by the different role assignments of two tables in the proposed algorithm. EM table with (m * 1) dimension is designed to record the distance information, reflecting the learning process of the robot. Q table is adopted as an auxiliary guidance for the experience transfer strategy and experience reuse strategy, and these strategies enable the robot accomplish the task even if the destination is changed or the path is blocked. Further, the learning efficiency of the robot in the EMQL algorithm is improved by the dual reward mechanism consisting of static reward and dynamic reward. The static reward is designed to prevent the robot from exploring a state node excessively. The dynamic reward is responsible for helping the robot avoid searching blindly in unknown environment. We test the effectiveness of the proposed algorithm on both grid maps and road network maps. The comparison results in planning time, iteration times and path length show that the performance of the EMQL algorithm is superior to Q-learning algorithm in convergence speed and optimization ability. Additionally, the practicability of the proposed algorithm is validated in a real-world experiment using the Turtlebot3 burger robot. INDEX TERMSPath planning, Q-learning, experience memory, experience transfer, experience reuse. HUI LU (Senior Member, IEEE) received the Ph.D. degree in navigation, guidance and control from Harbin Engineering University, Harbin, China, in 2004. She is currently a Professor with Beihang University and a member of the Shaanxi Key Laboratory of Integrated and Intelligent Navigation. Her research interests include information and communication systems, intelligent optimization, and fault diagnosis and prediction.
Progressive secret image sharing (PSIS) scheme attracts the interests of researchers in recent years. Many approaches have been proposed to construct PSIS schemes. In most of these schemes, the size of the shadow is expanded from the original image. On the contrary, polynomial-based PSIS can reduce shadow size from the original image. Recently, Yang and Huang proposed a polynomial-based (k, n) PSIS, where the image can be progressively reconstructed from k to n shadows. However, the problem of Yang-Huang's scheme is that the percentage of the recovered partial image from t shadows is extremely low when t is close to k. Later, Yang and Chu constructed another polynomial-based (k, n) PSIS with smooth property to solve this problem, but the size of the shadow is expanded greatly from Yang-Huang' scheme. In this paper, we propose a new (k, n) PSIS based on polynomial to overcome the drawbacks of these two schemes. In our scheme, t shadows (t is close to k) can recover more percentage partial image than Yang-Huang's scheme with a little shadow size expansion; comparing with Yang-Chu's scheme, our scheme achieves almost the same smooth property with much smaller shadow size. INDEX TERMS Interpolated polynomial, progressive secret image sharing, shadow size, smooth.
This paper proposes a novel machine learning-based scheme for the automatic analysis of authentication and key agreement protocols. Considering the traditional formal protocol analysis schemes, their analysis accuracies depend heavily on the prior knowledge possessed by the analyst and the subjective understanding of the protocol. The rapid development of artificial intelligence in security field shows that the ideal way to get rid of the dependency is to use machine learning. Hence, we elaborately compare more than 2000 protocol analysis results and select 500 most representative ones of them to build a protocol dataset. Combining the protocol representation method of traditional schemes, these selected protocols are expressed as weight matrixes based on security components. Furthermore, a machine learningbased security analysis model is proposed to automatically find the attacks of the protocol. For now, three types of attacks against authentication and key agreement protocols can be identified based on our model. And experiment results show that it can reach almost 72% upper-bound performance. From the derivative of the accuracy curves, it can be inferred that the performance of our scheme will definitely get better as the dataset expands. Keywords Authentication protocols Á Machine learning Á Formal analysis of protocol security Á Protocol dataset Zhuo Ma and Yang Liu have contributed equally to this work.
For a multi-robot system, the accurate global map building based on a local map obtained by a single robot is an essential issue. The map building process is always divided into three stages: single-robot map acquisition, multi-robot map transmission, and multi-robot map merging. Based on the different stages of map building, this paper proposes a multi-stage optimization (MSO) method to improve the accuracy of the global map. In the map acquisition stage, we windowed the map based on the position of the robot to obtain the local map. Furthermore, we adopted the extended Kalman filter (EKF) to improve the positioning accuracy, thereby enhancing the accuracy of the map acquisition by the single robot. In the map transmission stage, considering the robustness of the multi-robot system in the real environment, we designed a dynamic self-organized communication topology (DSCT) based on the master and slave sketch to ensure the efficiency and accuracy of map transferring. In the map merging stage, multi-layer information filtering (MLIF) was investigated to increase the accuracy of the global map. We performed simulation experiments on the Gazebo platform and compared the result of the proposed method with that of classic map building methods. In addition, the practicability of this method has been verified on the Turtlebot3 burger robot.Experimental results proved that the MSO method improves the accuracy of the global map built by the multi-robot system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.