A Novel Behavior-Based Virus Detection Method for Smart Mobile Terminals

The security of smart mobile terminals has been an increasingly important issue in recent years. While there are extensive researches on virus detections for smart mobile terminals, most of them share the same framework of virus detection as that for personal computers, and few of them tackle the problem from the standpoint of detection methodology. In this paper, we propose a behavior-based virus detection method for smart mobile terminals which signals the existence of malicious code through identifying the anomaly of user behaviors. We first propose a model to collect and analyze user behaviors and then present a polynomial time algorithm for the virus detection. Next, we evaluate this algorithm by testing it with two commercial malwares and one malware written by ourselves and show that our algorithm enjoys a high virus detection rate. Finally, we notice that the rate of change of the virus detection rate of the algorithm with respect to thresholds matches the real-world situation of user behaviors, which indicates that the proposed algorithm is feasible.

Download Full-text

Behavior-based virus detection method using multi-class support vector machine

Journal of Computer Applications ◽

10.3724/sp.j.1087.2010.00181 ◽

2010 ◽

Vol 30 (1) ◽

pp. 181-185

Author(s):

Lan-sheng HAN ◽

Meng-song ZOU ◽

Qi-wen LIU ◽

Ming LIU

Keyword(s):

Support Vector Machine ◽

Detection Method ◽

Virus Detection ◽

Support Vector ◽

Behavior Based

Download Full-text

Deepfake Detection Using the Rate of Change between Frames Based on Computer Vision

Sensors ◽

10.3390/s21217367 ◽

2021 ◽

Vol 21 (21) ◽

pp. 7367

Author(s):

Gihun Lee ◽

Mihui Kim

Keyword(s):

Artificial Intelligence ◽

Computer Vision ◽

Detection Rate ◽

Detection Method ◽

Big Data Analysis ◽

Rate Of Change ◽

Digital Content ◽

Machine Learning Method ◽

The Matrix ◽

Artificial Intelligence Technology

Recently, artificial intelligence has been successfully used in fields, such as computer vision, voice, and big data analysis. However, various problems, such as security, privacy, and ethics, also occur owing to the development of artificial intelligence. One such problem are deepfakes. Deepfake is a compound word for deep learning and fake. It refers to a fake video created using artificial intelligence technology or the production process itself. Deepfakes can be exploited for political abuse, pornography, and fake information. This paper proposes a method to determine integrity by analyzing the computer vision features of digital content. The proposed method extracts the rate of change in the computer vision features of adjacent frames and then checks whether the video is manipulated. The test demonstrated the highest detection rate of 97% compared to the existing method or machine learning method. It also maintained the highest detection rate of 96%, even for the test that manipulates the matrix of the image to avoid the convolutional neural network detection method.

Download Full-text

The Optimization Analysis for the Original and Manipulation Identification of Illegally Filmed Images

Applied Sciences ◽

10.3390/app11115220 ◽

2021 ◽

Vol 11 (11) ◽

pp. 5220

Author(s):

Soohyeon Choi ◽

Dohoon Kim

Keyword(s):

Social Media ◽

Mobile Device ◽

Detection Rate ◽

Precise Measurement ◽

Detection Method ◽

Optimization Analysis ◽

Storage Devices ◽

Digital Forensic ◽

Attribute Information ◽

Measurement Approach

Illegally filmed images, the sharing of non-consensually filmed images over social media, and the secret recording and distribution of celebrity images are increasing. To catch distributors of illegally filmed images, many investigation techniques based on an analysis of the file attribute information of the original images have been introduced. As forensic science advances, various types of anti-forensic technologies are being produced, requiring investigators to open and analyze all videos from the suspect’s storage devices, raising the question of the invasion of privacy during the investigation. The suspect can even file a lawsuit, which makes issuing a warrant and conducting an investigation difficult. Thus, it is necessary to detect the original and manipulated images without needing to directly go through multiple videos. We propose an optimization analysis and detection method for extracting original and manipulated images from seized devices of suspects. In addition, to increase the detection rate of both original and manipulated images, we suggest a precise measurement approach for comparative thresholds. Thus, the proposed method is a new digital forensic methodology for comparing and identifying original and manipulated images accurately without the need for opening videos individually in a suspect’s mobile device.

Download Full-text

Detection Method Of Students Classroom Learning Behavior Based On Parallel Classification Algorithm

International Journal of Continuing Engineering Education and Life-Long Learning ◽

10.1504/ijceell.2022.10038646 ◽

2022 ◽

Vol 32 (1) ◽

pp. 1

Author(s):

Degang Lai ◽

Ke Wang

Keyword(s):

Detection Method ◽

Classification Algorithm ◽

Learning Behavior ◽

Classroom Learning ◽

Behavior Based

Download Full-text

A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video

Journal of Advanced Transportation ◽

10.1155/2018/7075814 ◽

2018 ◽

Vol 2018 ◽

pp. 1-11 ◽

Cited By ~ 9

Author(s):

Xun Li ◽

Yao Liu ◽

Zhengfan Zhao ◽

Yue Zhang ◽

Li He

Keyword(s):

Detection Rate ◽

Detection Method ◽

Training Model ◽

Learning Approach ◽

Flow State ◽

False Detection Rate ◽

False Detection ◽

Road Vehicles ◽

Traffic Video ◽

Flow States

Vehicle detection is expected to be robust and efficient in various scenes. We propose a multivehicle detection method, which consists of YOLO under the Darknet framework. We also improve the YOLO-voc structure according to the change of the target scene and traffic flow. The classification training model is obtained based on ImageNet and the parameters are fine-tuned according to the training results and the vehicle characteristics. Finally, we obtain an effective YOLO-vocRV network for road vehicles detection. In order to verify the performance of our method, the experiment is carried out on different vehicle flow states and compared with the classical YOLO-voc, YOLO 9000, and YOLO v3. The experimental results show that our method achieves the detection rate of 98.6% in free flow state, 97.8% in synchronous flow state, and 96.3% in blocking flow state, respectively. In addition, our proposed method has less false detection rate than previous works and shows good robustness.

Download Full-text

PCR Detection of Respiratory Pathogens in Asymptomatic and Symptomatic Adults

Journal of Clinical Microbiology ◽

10.1128/jcm.00716-18 ◽

2018 ◽

Vol 57 (1) ◽

Cited By ~ 2

Author(s):

Nicklas Sundell ◽

Lars-Magnus Andersson ◽

Robin Brittain-Long ◽

Pär-Daniel Sundvall ◽

Åsa Alsiö ◽

...

Keyword(s):

Detection Rate ◽

Virus Detection ◽

Symptomatic Patient ◽

Reference Population ◽

Respiratory Pathogens ◽

Upper Airways ◽

Content Type ◽

Asymptomatic Subjects ◽

Hospital Emergency Departments

ABSTRACTThe frequency of viral respiratory pathogens in asymptomatic subjects is poorly defined. The aim of this study was to explore the prevalence of respiratory pathogens in the upper airways of asymptomatic adults, compared with a reference population of symptomatic patients sampled in the same centers during the same period. Nasopharyngeal (NP) swab samples were prospectively collected from adults with and without ongoing symptoms of respiratory tract infection (RTI) during 12 consecutive months, in primary care centers and hospital emergency departments, and analyzed for respiratory pathogens by a PCR panel detecting 16 viruses and four bacteria. Altogether, 444 asymptomatic and 75 symptomatic subjects completed sampling and follow-up (FU) at day 7. In the asymptomatic subjects, the detection rate of viruses was low (4.3%), and the most common virus detected was rhinovirus (3.2%).Streptococcus pneumoniaewas found in 5.6% of the asymptomatic subjects andHaemophilus influenzaein 1.4%. The only factor independently associated with low viral detection rate in asymptomatic subjects was age ≥65 years (P = 0.04). An increased detection rate of bacteria was seen in asymptomatic subjects who were currently smoking (P < 0.01) and who had any chronic condition (P < 0.01). We conclude that detection of respiratory viruses in asymptomatic adults is uncommon, suggesting that a positive PCR result from a symptomatic patient likely is relevant for ongoing respiratory symptoms. Age influences the likelihood of virus detection among asymptomatic adults, and smoking and comorbidities may increase the prevalence of bacterial pathogens in the upper airways.

Download Full-text

A Soft-YoloV4 for High-Performance Head Detection and Counting

Mathematics ◽

10.3390/math9233096 ◽

2021 ◽

Vol 9 (23) ◽

pp. 3096

Author(s):

Zhen Zhang ◽

Shihao Xia ◽

Yuxing Cai ◽

Cuimei Yang ◽

Shaoning Zeng

Keyword(s):

High Performance ◽

Detection Rate ◽

Detection Method ◽

State Of The Art ◽

Counting Method ◽

People Counting ◽

Detection Model ◽

Detection And Counting ◽

Head Detection ◽

Ap Value

Blockage of pedestrians will cause inaccurate people counting, and people’s heads are easily blocked by each other in crowded occasions. To reduce missed detections as much as possible and improve the capability of the detection model, this paper proposes a new people counting method, named Soft-YoloV4, by attenuating the score of adjacent detection frames to prevent the occurrence of missed detection. The proposed Soft-YoloV4 improves the accuracy of people counting and reduces the incorrect elimination of the detection frames when heads are blocked by each other. Compared with the state-of-the-art YoloV4, the AP value of the proposed head detection method is increased from 88.52 to 90.54%. The Soft-YoloV4 model has much higher robustness and a lower missed detection rate for head detection, and therefore it dramatically improves the accuracy of people counting.

Download Full-text

Bacterial colonies detecting and counting based on enhanced CNN detection method

E3S Web of Conferences ◽

10.1051/e3sconf/202123302012 ◽

2021 ◽

Vol 233 ◽

pp. 02012

Author(s):

Shousheng Liu ◽

Zhigang Gai ◽

Xu Chai ◽

Fengxiang Guo ◽

Mei Zhang ◽

...

Keyword(s):

Target Detection ◽

Error Detection ◽

Detection Rate ◽

Detection Method ◽

Difficult Problem ◽

Detection Methods ◽

Detection Accuracy ◽

Detection Model ◽

Confidence Threshold ◽

Small Targets

Bacterial colonies detecting and counting is tedious and time-consuming work. Fortunately CNN (convolutional neural network) detection methods are effective for target detection. The bacterial colonies are a kind of small targets, which have been a difficult problem in the field of target detection technology. This paper proposes a small target enhancement detection method based on double CNNs, which can not only improve the detection accuracy, but also maintain the detection speed similar to the general detection model. The detection method uses double CNNs. The first CNN uses SSD_MOBILENET_V1 network with both target positioning and target recognition functions. The candidate targets are screened out with a low confidence threshold, which can ensure no missing detection of small targets. The second CNN obtains candidate target regions according to the first round of detection, intercepts image sub-blocks one by one, uses the MOBILENET_V1 network to filter out targets with a higher confidence threshold, which can ensure good detection of small targets. Through the two-round enhancement detection method has been transplanted to the embedded platform NVIDIA Jetson AGX Xavier, the detection accuracy of small targets is significantly improved, and the target error detection rate and missed detection rate are reduced to less than 1%.

Download Full-text