Predicting and Classifying User Identification Code System Based on Support Vector Machines

In digital fingerprinting, preventing piracy of images by colluders is an important and tedious issue. Each image will be embedded with a unique User IDentification （UID） code that is the fingerprint for tracking the authorized user. The proposed hiding scheme makes use of a random number generator to scramble two copies of a UID, which will then be hidden in the randomly selected medium frequency coefficients of the host image. The linear support vector machine （SVM） will be used to train classifications by calculating the normalized correlation （NC） for the 2class UID codes. The trained classifications will be the models used for identifying unreadable UID codes. Experimental results showed that the success of predicting the unreadable UID codes can be increased by applying SVM. The proposed scheme can be used to provide protections to intellectual property rights of digital images aad to keep track of users to prevent collaborative piracies.

Adding Sub-chain Method for Structural Synthesis of Planar Closed Kinematic Chains

For at least the past five decades,structural synthesis has been used as a main means of finding better mechanisms with some predefined function.In structural synthesis,isomorphism identification is still a problem unsolved well,and to solve this problem is very significant to the design of new mechanisms.According to the given degree of freedom（DOF） and link connection property of planar closed chain mechanisms,vertex assortment is obtained.For solving the isomorphism problem,a method of the adding sub-chains is proposed with the detailed steps and algorithms in the synthesizing process.Employing this method,the identification code and formation code of every topological structure are achieved,therefore many isomorphic structures could be eliminated in time during structural synthesis by comparing those codes among different topological graphs,resulting in the improvement of synthesizing efficiency and accuracy,and the approach for eliminating rigid sub-chains in and after the synthesizing process is also presented.Some examples are given,including how to add sub-chains,how to detect simple rigid sub-chains and how to obtain identification codes and formulation codes et al.Using the adding sub-chain method,the relative information of some common topological graphs is given in the form of table.The comparison result is coincident with many literatures,so the correctness of the adding sub-chain method is convinced.This method will greatly improve the synthesizing efficiency and accuracy,and has a good potential for application.

Evil-hunter: a novel web shell detection system based on scoring scheme

In order to detect web shells that hackers inject into web servers by exploiting system vulnerabilities or web page open sources, a novel web shell detection system based on the scoring scheme is proposed, named Evil-hunter. First, a large set of malicious function samples normally used in web shells are collected from various sources on the Internet and security forums. Secondly, according to the danger level and the frequency of using these malicious functions in the web shells as well as in legal web applications, an assigning score strategy for each malicious sample is devised. Then, the appropriate score threshold value for each sample is obtained from the results of a statistical analysis. Finally, based on the threshold value, a simple algorithm is presented to identify files that contain web shells in web applications. The experimental results show that compared with other approaches, Evil-hunter can identify web shells more efficiently and accurately.