Hard-coded backdoor detection method based on semantic conflict by Anxiang HU, Da XIAO, Shichen GUO, Shengli LIU

“…The current router security issues focus on the mining and utilization of memory-type vulnerabilities, but there is low interest in detecting backdoors.Hard-coded backdoor is one of the most common backdoors, which is simple and convenient to set up and can be implemented with only a small amount of code.However, it is difficult to be discovered and often causes serious safety hazard and economic loss.The triggering process of hard-coded backdoor is inseparable from string comparison functions.Therefore, the detection of hard-coded backdoors relies on string comparison functions, which are mainly divided into static analysis method and symbolic execution method.The former has a high degree of automation, but has a high false positive rate and poor detection results.The latter has a high accuracy rate, but cannot automate large-scale detection of firmware, and faces the problem of path explosion or even unable to constrain solution.Aiming at the above problems, a hard-coded backdoor detection algorithm based on string text semantic conflict (Stect) was proposed since static analysis and the think of stain analysis.Stect started from the commonly used string comparison functions, combined with the characteristics of MIPS and ARM architectures, and extracted a set of paths with the same start and end nodes using function call relationships, control flow graphs, and branching selection dependent strings.If the strings in the successfully verified set of paths have semantic conflict, it means that there is a hard-coded backdoor in the router firmware.In order to evaluate the detection effect of Stect, 1 074 collected device images were tested and compared with other backdoor detection methods.Experimental results show that Stect has a better detection effect compared with existing backdoor detection methods including Costin and Stringer: 8 hard-coded backdoor images detected from image data set, and the recall rate reached 88.89%.…”
Get full text

Business process mining based insider threat detection system by Tai-ming ZHU, Yuan-bo GUO, An-kang JU, Jun MA

“…Current intrusion detection systems are mostly for detecting external attacks,but sometimes the internal staff may bring greater harm to organizations in information security.Traditional insider threat detection methods of-ten do not combine the behavior of people with business activities,making the threat detection rate to be improved.An insider threat detection system based on business process mining from two aspects was proposed,the implementation of insider threats and the impact of threats on system services.Firstly,the normal control flow model of business ac-tivities and the normal behavior profile of each operator were established by mining the training log.Then,the actual behavior of the operators was compared with the pre-established normal behavior contours during the operation of the system,which was supplemented by control flow anomaly detection and performance anomaly detection of business processes,in order to discover insider threats.A variety of anomalies were defined and the corresponding detection algorithms were given.Experiments were performed on the ProM platform.The results show the designed system is effective.…”
Get full text

Semi-supervised permutation invariant particle-level anomaly detection by Gabriel Matos, Elena Busch, Ki Ryeong Park, Julia Gonski

“…Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. …”
Get full text

Android malware detection method based on deep neural network by Fan CHAO, Zhi YANG, Xuehui DU, Yan SUN

“…Android is increasingly facing the threat of malware attacks.It is difficult to effectively detect large-sample and multi-class malware for traditional machine learning methods such as support vector machine,method for Android malware detection and family classification based on deep neural network was proposed.Based on the comprehensive extraction of application components,Intent Filter,permissions,and data flow,the method performed an effective feature selection to reduce dimensions,and conducted a large-sample detection and multi-class classification for malware based on deep neural network.The experimental results show that the method can conduct an effective detection and classification.The accuracy of binary classification between benign and malicious Apps is 97.73%,and the accuracy of family multi-class classification can reach 93.54%,which is higher than other machine learning algorithms.…”
Get full text

A Study of Mixed Non-Motorized Traffic Flow Characteristics and Capacity Based on Multi-Source Video Data by Guobin Gu, Xin Sun, Benxiao Lou, Xiang Wang, Bingheng Yang, Jianqiu Chen, Dan Zhou, Shiqian Huang, Qingwei Hu, Chun Bao

“…Initially, UAVs and video cameras are used to capture videos of mixed non-motorized traffic flow. The video data were processed with an image detection algorithm based on the YOLO convolutional neural network and a video tracking algorithm using the DeepSORT multi-target tracking model, extracting data on traffic flow, density, speed, and rider characteristics. …”
Get full text

Image Reconstruction Algorithm Based on Spectral Projected Gradient Pursuit for Electrical Capacitance Tomography by WANG Li-li, LIU Hong-bo, CHEN De-yun, CHEN Feng

“…Accuracy and speed are important indicators to detect the image reconstruction algorithm for electrical capacitance tomography. …”
Get full text

Optimization of the control system of BP-PID rice polishing unit based on WAO algorithm by HUANG Jinliang, ZHOU Jin, YU Wei

“…ObjectiveAddress the current issues of poor internal flow stability, low single-machine efficiency, and subpar polishing quality in rice polishing units.MethodsFirstly, the traditional polishing machine was improved, its control parameters were clarified, and the mathematical model of the rice polishing unit was established. …”
Get full text

An RFCSO-based grid stability enhancement by integrating solar photovoltaic systems with multilevel unified power flow controllers by Swetha Monica Indukuri, Alok Kumar Singh, D. Vijaya Kumar

“…The power is then fed into the grid, which supplies sensitive critical and nonlinear loads. Three-phase fault detection mechanisms and series transformers manage the power flow and fault conditions. …”
Get full text

A Keyframe Extraction Method for Assembly Line Operation Videos Based on Optical Flow Estimation and ORB Features by Xiaoyu Gao, Hua Xiang, Tongxi Wang, Wei Zhan, Mengxue Xie, Lingxuan Zhang, Muyu Lin

“…Each video frame is first encoded into a feature vector using the ORB algorithm and a bag-of-visual-words model. Optical flow is then calculated using the DIS algorithm, allowing frames to be categorized by motion intensity. …”
Get full text

Subway Sudden Passenger Flow Prediction Method Based on Two Factors: Case Study of the Dongsishitiao Station in Beijing by Chengguang Xie, Xiaofeng Li, Bingfa Chen, Feng Lin, Yushun Lin, Hainan Huang

“…The wavelet neural network (WNN) model was used to detect the sudden passenger flow, and subsequently, it is optimized by the genetic algorithm (GA), according to two-factor data characteristics. …”
Get full text

Assessing SWOT's Hydraulic Visibility on the Rhine: Precision Flow Lines and Slope‐Based Flood Wave Propagation Signatures by T. Ledauphin, P.‐A. Garambois, K. Larnier, M. Azzoni, C. Emery, N. Picot, S. Amzil, R. Fjørtoft, J. Maxant, H. Yésou

“…SWOT data also revealed temporal river profile variations, capturing slope changes, flow waves, riffles, pools, alluvial deposits, and recharge zones. …”
Get full text

Function encoding based approach for App clone detection in cloud environment by Jia YANG, Cai FU, Lansheng HAN, Hongwei LU, Jingliang LIU

“…An efficient function-based encoding scheme in the cloud environment for detecting the cloned Apps was designed,called Pentagon.Firstly,a basic block feature extraction method was proposed.Secondly,a monotonic encoding algorithm for the App function was designed,which encoded the function based on the control flow graph structure and basic block attributes.Finally,a three-party libraries filtering method was proposed by using an efficient clustering algorithm based on the function feature.Experiments verified the effectiveness of the proposed scheme.The average search time is close to 79 ms,and the clone detection accuracy achieves 97.6%.…”
Get full text

Research on Fusion of Locomotive Safety Monitoring and Detection Data and Its Application by GONG Li, QIAO Bin, ZHAO Chao, YAO Kai

“…This paper introduced a scheme of integration and fusion of locomotive safety monitoring and detection data by a task flow based ETL data extraction algorithm. …”
Get full text

Detecting unsafe behavior in neural network imitation policies for caregiving robotics by Andrii Tytarenko

“…Novel solutions proposed include ensemble predictors and adaptations of the normalizing flow-based algorithm for early anomaly detection. …”
Get full text

Early Sweet Potato Plant Detection Method Based on YOLOv8s (ESPPD-YOLO): A Model for Early Sweet Potato Plant Detection in a Complex Field Environment by Kang Xu, Wenbin Sun, Dongquan Chen, Yiren Qing, Jiejie Xing, Ranbing Yang

“…Aiming at the problems of low detection accuracy of sweet potato plants and the complex of target detection models in natural environments, an improved algorithm based on YOLOv8s is proposed, which can accurately identify early sweet potato plants. …”
Get full text

BCAST IDS: A Novel Network Intrusion Detection System for Broadcast Networks by Javier Gombao

“…A modern approach to enhancing the capabilities of NIDSs is the use of machine learning (ML) algorithms that predict attacks based on data. This study introduces a novel and lightweight NIDS called Broadcast IDS (BCAST IDS) that uses specific network traffic patterns and the Isolation Forest algorithm to detect anomalies in broadcast networks. …”
Get full text

Identification and evaluation of the effective criteria for detection of congestion in a smart city by Anita Mohanty, Subrat Kumar Mohanty, Bhagyalaxmi Jena, Ambarish G. Mohapatra, Ahmed N. Rashid, Ashish Khanna, Deepak Gupta

“…The result can be a better technique for congestion detection as it requires low installation cost and can be incorporate in vehicles for congestion avoidance which will alternatively improve the traffic flow.…”
Get full text

Leak detection and localization in water distribution systems via multilayer networks by Daniel Barros, Ariele Zanfei, Andrea Menapace, Gustavo Meirelles, Manuel Herrera, Bruno Brentan

“…Due to the intrinsic interconnected feature of water flow, including losses, this study proposes a methodology based on graph correlation and multilayer network analysis for leak detection and localization in WDNs with multiple components (infrastructure, control devices, hydraulic sensors). …”
Get full text

DFTD-YOLO: Lightweight Multi-Target Detection From Unmanned Aerial Vehicle Viewpoints by Yuteng Chen, Zhaoguang Liu

“…The network better balances information transfer between shallow and deep layers through a detailed information extraction module and an abstract feature information aggregation module, effectively reducing the loss of detail information with gradient flow and improving detection performance. In addition, we designed a new detection head called the TDD-Head. …”
Get full text

Balanced Multi-Class Network Intrusion Detection Using Machine Learning by Faraz Ahmad Khan, Asghar Ali Shah, Nizal Alshammry, Saifullah Saif, Wasim Khan, Muhammad Osama Malik, Zahid Ullah

“…This work aims to design an effective NIDS that addresses the current limitation using machine learning models trained on reliable flow-based data (CICIDS-2017). The system will improve the detection accuracy and reduce false alarms in high-speed network environments. …”
Get full text