A data reduction scheme for active authentication of legitimate smartphone owner using informative apps ranking

Smartphones are vulnerable to fraudulent use despite having strong authentication mechanisms. Active authentication based on behavioral biometrics is a solution to protect the privacy of data in smart devices. Machine-learning-based frameworks are effective for active authentication. However, the success of any machine-learning-based techniques depends highly on the relevancy of the data in hand for training. In addition, the training time should be very efficient. Keeping in view both issues, we’ve explored a novel fraudulent user detection method based solely on the app usage patterns of legitimate users. We hypothesized that every user has a unique pattern hidden in his/her usage of apps. Motivated by this observation, we’ve designed a way to obtain training data, which can be used by any machine learning model for effective authentication. To achieve better accuracy with reduced training time, we removed data instances related to any specific user from the training samples which did not contain any apps from the user-specific priority list. An information theoretic app ranking scheme was used to prepare a user-targeted apps priority list. Predictability of each instance related to a candidate app was calculated by using a knockout approach. Finally, a weighted rank was calculated for each app specific to every user. Instances with low ranked apps were removed to derive the reduced training set. Two datasets as well as seven classifiers for experimentation revealed that our reduced training data significantly lowered the prediction error rates in the context of classifying the legitimate user of a smartphone.     

加密认证技术及其在网络取证中的应用

针对网络数据传输安全的需要,在传输层之上加入了SSL(SecureSocketLayer)层,通过SSL层,对应用层提供安全、可靠、便捷的数据传输服务。     

Web Page Forensics: A Web Spider Based Approach

Cyber-crimes are growing rapidly,so it is important to obtain the digital evidence on the web page.Usually,people can examine the browser history on the client side and data files on the server side,but both of them have shortcomings in real criminal investigation.To overcome the weakness,this paper designs a web page forensic scheme to snapshot the pages from web servers with the help of web spider.Also,it designs several steps to improve the trustworthiness of these pages.All the pages will be dumped in local database which can be presented as reliable evidence on the court.     

Empirical Evaluation of Information Leakage Detection Using Net-flow Analysis

Because of the widespread of Trojans,organizations and Internet users become more vulnerable to the threat of information leakage.This paper describes an information leakage detection system（ ILDS） to detect sensitive information leakage caused by Trojan.In particular,the principles of the system are based on the analysis of net-flows in four perspectives： heartbeat behavior analysis,DNS abnormal analysis,uploaddownload ratio and content analysis.Heartbeat behavior analysis and DNS abnormal analysis are used to detect the existence of Trojans while upload-download ratio and content analysis can quickly detect when the information leakage happens.Experiments indicate that the system is reliable and efficient in detecting information leakage.The system can also help to collect and preserve digital evidence when information leakage incident occurs.     

Smartphone user segmentation based on app usage sequence with neural networks

The term user segmentation refers to classifying users into groups depending on their specific needs, characteristics, or behaviors. It is a key element of product development and marketing in many industries, such as the smartphone industry, which employs user segmentation to gather information about usage logs, to produce new products for such specific groups of users. However, previous studies on smartphone user segmentation have been primarily based on demographics and reported usage, which are inherently subjective and prone to skew by the observers and participants. Hamka et al. (2014) was the first to conduct a study, in which smartphone user segmentation was performed using log data collected through smartphone measurements. However, they focused only on network usage and the number of apps used, and not on characteristics or preferences. In this study, we proposed novel ways of segmenting smartphone users based on app usage sequences collected from smartphone logs. We proposed a variant of seq2seq architecture combining the advantages of previous deep neural networks: neural embedding architecture and seq2seq architecture. Furthermore, we compared the user segmentation results of the proposed method with an answer set of segmentation results conducted by domain experts. These experiments demonstrated that the proposed method effectively determines similarities between usage sequences and outperforms existing user segmentation methods.     

Relationship analysis between body flexion angles and smartphone tilt during smartphone use

Although smartphones are used as essential devices in everyday life, many users are exposed to joint diseases owing to prolonged use. The objectives of this study were to analyze how posture and smartphone tasks affect various body flexion angles and develop an algorithm to classify posture/task and estimate body flexion angles using smartphone tilt data. Eighteen participants performed two tasks (playing a game and reading news) in two postures (sitting and standing) in a laboratory environment. The three-axis orientation data (azimuth, pitch, and roll) of the smartphone and the participants’ body flexion angles were measured simultaneously. This study found that the cervical, thoracic, lumbar, and overall flexion angles were all statistically significantly different depending on the posture of the smartphone user, and the cervical flexion angle was significantly different depending on the task. Furthermore, task and task × posture can be classified with high accuracy based on smartphone tilt data, and tilt data had a high correlation with body flexion angles. Relevance to industry: The results of this study can be used as a reference for designing various products and interfaces for neck health. The results can be applied as a smartphone alarm or a built-in application, which can inform the user of the need to stretch his or her neck.     

Using mobile devices as scientific measurement instruments: Reliable android task scheduling

In various usage scenarios, smartphones are used as measuring instruments to systematically and unobtrusively collect data measurements (e.g., sensor data, user activity, phone usage data). Unfortunately, in the race towards extending battery life and improving privacy, mobile phone manufacturers are gradually restricting developers in (frequently) scheduling background (sensing) tasks and impede the exact scheduling of their execution time (i.e., Android’s “best effort” approach). This evolution hampers successful deployment of smartphones in sensing applications in scientific contexts, with unreliable and incomplete sampling rates frequently reported in literature. In this article, we discuss the ins and outs of Android’s background tasks scheduling mechanism, and formulate guidelines for developers to successfully implement reliable task scheduling. Implementing these guidelines, we present a software library, agnostic from the underlying Android scheduling mechanisms and restrictions, that allows Android developers to reliably schedule tasks with a maximum sampling rate of one minute. Our evaluation demonstrates the use and versatility of our task scheduler, and experimentally confirms its reliability and acceptable energy usage.     

CNN spatiotemporal features and fusion for surveillance video forgery detection

Surveillance cameras are widely used to provide protection and security; also their videos are used as strong evidences in the courts. Through the availability of video editing tools, it has become easy to distort these evidences. Sometimes, to hide the traces of forgery, some post-processing operations are performed after editing. Hence, the authenticity and integrity of surveillance videos have become urgent to scientifically validate. In this paper, we propose inter-frame forgeries (frame deletion, frame insertion, and frame duplication) detection system using 2D convolution neural network (2D-CNN) of spatiotemporal information and fusion for deep automatically feature extraction; Gaussian RBF multi-class support vector machine (RBF-MSVM) is used for classification process. The experimental results show that the efficiency of the proposed system for detecting all inter-frame forgeries, even when the forged videos have undergone additional post-processing operations such as Gaussian noise, Gaussian blurring, brightness modifications and compression.     

Language,modality, and mobile media use experiences: Social responses to smartphone cues in a task-oriented context

With people’s growing use of virtual agents and voice assistants on smartphones, researchers have pointed out that mobile phones are not only acting as intermediaries that connect users from different places, but also communication terminals that present different combinations of social cues. This study applies the Computers are Social Actors paradigm in human-phone interaction and postulates that compared to non-anthropomorphic language and text cues, anthropomorphic language and vocal cues will have more effects on users’ social responses to smartphones. This study also explores the role of individual differences in users’ social responses to smartphones. Based on a lab experiment using a between-subjects factorial design, the study suggests that although anthropomorphic language and voice-based information did not have main effects on users’ social responses, people’s mobile media usage and intensive phone use interacted with these cues in their social responses to the smartphones. In addition, this study implies that it is the combination of social cues, individual differences, and communication contexts that contributes to people’s social reactions to the smartphones. The findings of the study can inform user interface design and precipitate further discussion about the ethical issues in human-phone interaction.     

一种检测C&W对抗样本图像的盲取证算法

对抗样本图像能欺骗深度学习网络,亟待对抗样本防御机制以增强深度学习模型的安全性。C&W攻击是目前较热门的一种白盒攻击算法,它产生的对抗样本具有图像质量高、可转移、攻击性强、难防御等特点。本文以C&W攻击生成的对抗样本为研究对象,采用数字图像取证的思路,力图实现C&W对抗样本的检测,拒绝对抗样本输入深度学习网络。基于对抗样本中的对抗扰动易被破坏的假设,我们设计了基于FFDNet滤波器的检测算法。具体来说,FFDNet是一种基于深度卷积网络CNN的平滑滤波器,它能破坏对抗扰动,导致深度学习模型对对抗样本滤波前后的输出不一致。我们判断输出不一致的待测图像为C&W对抗样本。我们在ImageNet-1000图像库上针对经典的ResNet深度网络生成了6种C&W对抗样本。实验结果表明本文方法能较好地检测C&W对抗样本。相较于已有工作,本文方法不仅极大地降低了虚警率,而且提升了C&W对抗样本的检测准确率。