Author: Tuan Sinung

Vandalism Detection in Wikipedia

Abstract—With millions of users, Wikipedia is now the largest collaborative encyclopedia in the world. However, there is a growing problem of vandalism edit. Several previous works have developed either hand-designed or automated techniques to detect those vandalism edits. In this paper, we proposed a novel vandalism detection technique by combining spectral features of the nodes and the nodes’ neighborhood information with deep autoencoder’s representation learning. Our experimental testing has shown that our proposed method outperforms other standard learning algorithms such as k-nearest neighbors, support vector machine, and softmax classifier. Keywords—machine learning; security; data mining; signed network; wikipedia; vandalism detection;...

Read More

Towards Building Forensics Enabled Cloud Through Secure Logging-as-a-Service

Abstract Cloud computing is becoming a very popular computing paradigm because of its advantages, such as lower cost and high performance computing power. This increasing popularity has brought to light security concerns as well as interests from the law-enforcement community regarding cloud forensic investigations in the cloud environment. However, today’s cloud computing architectures often do not offer the necessary support for computer forensic investigations. Collecting logs, a very important activity in digital forensics, is not trivial in a cloud computing environment. Another problem is how to provide cloud logs to investigators while preserving users’ privacy and the integrity of...

Read More

Simple Batch Script for Live Forensics Data Collection on Windows

Basic Idea of Live Forensics Data Collection on Microsoft Windows System Computer Forensics deals with analysis after an incident or attack has occurred. The goals of this analysis are assessing the scope of the attack, how did the attack happen, what do we lose, who is the culprit, etcetera. The first thing to do is collecting data for that analysis purpose. There are two types of data for this. The first one is static data where the source computer for the data is turned off. The second one is live data where the source computer for the data can’t...

Read More

Inferring Mobile Apps from the Resource Usage Patterns

Abstract: Despite many applications, mobile cloud computing induces privacy concerns. In particular, when mobile device users offload the computation of a mobile app to the cloud, they may not want the cloud service provider (CSP) to know what kind of app they are using, since that information might be used to infer their personal activities and living habits. One possible way for the CSP to learn the type of an offloaded app is to observe the resource usage patterns of the app (e.g., CPU and memory usage), since different apps have different resource needs due to their distinct computation...

Read More

Razorback Transit Notification

1. Project Idea Razorback Transit (University of Arkansas bus) Riders need to know when is the right time to walk to the bus stop and hence do not spend much time waiting at the bus stop. This reason becomes more critical in cold Fall/Winter to reduce the chance of freezing in the bus stop. Based on already available data (from other people or estimation based on distance and crosswalk). However, as the more data collected from a particular user, it can be fitted and personalized to each user’s walking pace. This problem has not been addressed before. This problem is also...

Read More


Enter your email address to receive notifications of new posts by email.

Join 4 other subscribers


sinunk @ Github

Show my repositories


Pin It on Pinterest