Most of the sophisticated attacks in the modern age of cybercrime are based, among other things, on specialized phishing campaigns. A challenge in identifying phishing campaigns is defining a classification of patterns that can be generalized and used in different areas and campaigns of a different nature. Although efforts have been made to establish a general labeling scheme in their classification, there is still limited data labeled in such a format. The usual approaches are based on feature engineering to correctly identify phishing campaigns, exporting lexical, syntactic, and semantic features, e.g., previous phrases. In this context, the most recent approaches have taken advantage of modern neural network architectures to record hidden information at the phrase and text levels, e.g., Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs). However, these models lose semantic information related to the specific problem, resulting in a variation in their performance, depending on the different data sets and the corresponding standards used for labeling. In this paper, we propose to extend word embeddings with word vectors that indicate the semantic similarity of each word with each phishing campaigns template tag. These embedded keywords are calculated based on semantic subfields corresponding to each phishing campaign tag, constructed based on the automatic extraction of keywords representing these tags. Combining general word integrations with vectors is calculated based on word similarity using a set of sequential Kalman filters, which can then power any neural architecture such as LSTM or CNN to predict each phishing campaign. Our experiments use a data indicator to evaluate our approach and achieve remarkable results that reinforce the state-of-the-art.

At present network attack technology is constantly updated,which bring network security workers huge challenges. In view of the fact that the existing intrusion detection technology is difficult to detect multi-step fragmentation attacks, distributed attacks and evading attacks,a network intrusion detection algorithm called FSA algorithm is proposed based on finite state automaton (FSA) model in this paper, and the key implementation technology is analyzed.The state transition diagram is used to illustrate the attack triggering and transfer process,and according to different protocol data,four different mechanisms are designed to detect invasion based on FSA.Experiments show that the algorithm not only can more precisely detect common attacks,but also can detect the unobvious attacks such as distributed and fragment attack very well,which can not be detected by other detection technologies.It is believe that it removes the limitations of the current intrusion detection technology and has an important research and practice value.

No abstract

Based on the analysis of AJAX technologies, smart client and web service features, a framework of client access performance optimization under concurrent access environment is proposed. The main idea is as follows: first combining traditional web access with AJAX techniques and implementing partial refresh to improve user's experience effect; and then implement data caching and offline running to reduce the network traffic betteen client and server for sensitive application features, it also improve system stability and security. At the same time, in conjunction with the smart client in the serviceoriented data access method, it provide a web based service distributed data access to the underlying platform for the entire system's data access. Web services asynchronously through server side, so that as much as possible to reduce the client application block, then improve system's extendability and concurrency access performance.

No abstract