This PDF file contains the front matter associated with SPIE Proceedings Volume 9850, including the Title Page, Copyright information, Table of Contents, Introduction (if any), and Conference Committee listing.
The cyber spaces are increasingly becoming the battlefields between friendly and adversary forces, with normal users caught in the middle. Accordingly, planners of enterprise defensive policies and offensive cyber missions alike have an essential goal to minimize the impact of their own actions and adversaries’ attacks on normal operations of the commercial and government networks. To do this, the cyber analysis need accurate "cyber battle maps", where the functions, roles, and activities of individual and groups of devices and users are accurately identified.
Most of the research in cyber exploitation has focused on the identification of attacks, attackers, and their devices. Many tools exist for device profiling, malware identification, user attribution, and attack analysis. However, most of the tools are intrusive, sensitive to data obfuscation, or provide anomaly flagging and not able to correctly classify the semantics and causes of network activities. In this paper, we review existing solutions that can identify functional and social roles of entities in cyberspace, discuss their weaknesses, and propose an approach for developing functional and social layers of cyber battle maps.
This work addresses the problem of identifying the set of nodes in a power network critical to system operation. Formally, the CNA problem is the problem of identifying a minimum cardinality set of nodes to target in a power network in order to reduce throughput by a given factor. Since the defender may reroute flows in an attempt to restore throughput, the attack must anticipate and defeat this possibility. We develop here an algorithm to solve this problem. In our approach we model the problem as a bi-level optimization problem where the master problem attempts different attack combinations and the sub-problem responds with the best routing. The optimization problems that result from such a framework are mixed integer programs (MIPs), which we solve in our implementation using IBM CPLEX. The algorithm has been tested on several benchmark networks and appears to perform well. We have also developed variants that can be used for determining optimal restoration configuration post damage on large networks (4000 nodes, 8000 links) and for modeling propagation of failures after the initial attack. We report on computational experiments with these variants as well.
Honeypot application is a source of valuable data about attacks on the network. We run several SIP honeypots in various computer networks, which are separated geographically and logically. Each honeypot runs on public IP address and uses standard SIP PBX ports. All information gathered via honeypot is periodically sent to the centralized server. This server classifies all attack data by neural network algorithm. The paper describes optimizations of a neural network classifier, which lower the classification error. The article contains the comparison of two neural network algorithm used for the classification of validation data. The first is the original implementation of the neural network described in recent work; the second neural network uses further optimizations like input normalization or cross-entropy cost function. We also use other implementations of neural networks and machine learning classification algorithms. The comparison test their capabilities on validation data to find the optimal classifier. The article result shows promise for further development of an accurate SIP attack classification engine.
Multilayer Perceptron Networks with random hidden layers are very efficient at automatic feature extraction and offer significant performance improvements in the training process. They essentially employ large collection of fixed, random features, and are expedient for form-factor constrained embedded platforms. In this work, a reconfigurable and scalable architecture is proposed for the MLPs with random hidden layers with a customized building block based on CORDIC algorithm. The proposed architecture also exploits fixed point operations for area efficiency. The design is validated for classification on two different datasets. An accuracy of ~ 90% for MNIST dataset and 75% for gender classification on LFW dataset was observed. The hardware has 299 speed-up over the corresponding software realization.
This paper targets to highlight flight safety issues by applying data mining techniques to recorded flight data and proactively detecting abnormalities in certain flight phases. For this purpose, a result oriented method is offered which facilitates the process of post flight data analysis. In the first part of the study, a common time period of flight is defined and critical flight parameters are selected to be analyzed. Then the similarities of the flight parameters in time series basis are calculated for each flight by using Dynamic Time Warping (DTW) method. In the second part, hierarchical clustering technique is applied to the aggregate data matrix which is comprised of all the flights to be studied in terms of similarities among chosen parameters. Consequently, proximity levels among flight phases are determined. In the final part, an algorithm is constructed to distinguish outliers from clusters and classify them as suspicious flights.
This paper presents a method for detecting speech under stress using Self-Organizing Maps. Most people who are exposed to stressful situations can not adequately respond to stimuli. Army, police, and fire department occupy the largest part of the environment that are typical of an increased number of stressful situations. The role of men in action is controlled by the control center. Control commands should be adapted to the psychological state of a man in action. It is known that the psychological changes of the human body are also reflected physiologically, which consequently means the stress effected speech. Therefore, it is clear that the speech stress recognizing system is required in the security forces. One of the possible classifiers, which are popular for its flexibility, is a self-organizing map. It is one type of the artificial neural networks. Flexibility means independence classifier on the character of the input data. This feature is suitable for speech processing. Human Stress can be seen as a kind of emotional state. Mel-frequency cepstral coefficients, LPC coefficients, and prosody features were selected for input data. These coefficients were selected for their sensitivity to emotional changes. The calculation of the parameters was performed on speech recordings, which can be divided into two classes, namely the stress state recordings and normal state recordings. The benefit of the experiment is a method using SOM classifier for stress speech detection. Results showed the advantage of this method, which is input data flexibility.
This article describes a system for evaluating the credibility of recordings with emotional character. Sound recordings form Czech language database for training and testing systems of speech emotion recognition. These systems are designed to detect human emotions in his voice. The emotional state of man is useful in the security forces and emergency call service. Man in action (soldier, police officer and firefighter) is often exposed to stress. Information about the emotional state (his voice) will help to dispatch to adapt control commands for procedure intervention. Call agents of emergency call service must recognize the mental state of the caller to adjust the mood of the conversation. In this case, the evaluation of the psychological state is the key factor for successful intervention. A quality database of sound recordings is essential for the creation of the mentioned systems. There are quality databases such as Berlin Database of Emotional Speech or Humaine. The actors have created these databases in an audio studio. It means that the recordings contain simulated emotions, not real. Our research aims at creating a database of the Czech emotional recordings of real human speech. Collecting sound samples to the database is only one of the tasks. Another one, no less important, is to evaluate the significance of recordings from the perspective of emotional states. The design of a methodology for evaluating emotional recordings credibility is described in this article. The results describe the advantages and applicability of the developed method.
This article discusses the impact of multilayer neural network parameters for speaker identification. The main task of speaker identification is to find a specific person in the known set of speakers. It means that the voice of an unknown speaker (wanted person) belongs to a group of reference speakers from the voice database. One of the requests was to develop the text-independent system, which means to classify wanted person regardless of content and language. Multilayer neural network has been used for speaker identification in this research. Artificial neural network (ANN) needs to set parameters like activation function of neurons, steepness of activation functions, learning rate, the maximum number of iterations and a number of neurons in the hidden and output layers. ANN accuracy and validation time are directly influenced by the parameter settings. Different roles require different settings. Identification accuracy and ANN validation time were evaluated with the same input data but different parameter settings. The goal was to find parameters for the neural network with the highest precision and shortest validation time. Input data of neural networks are a Mel-frequency cepstral coefficients (MFCC). These parameters describe the properties of the vocal tract. Audio samples were recorded for all speakers in a laboratory environment. Training, testing and validation data set were split into 70, 15 and 15 %. The result of the research described in this article is different parameter setting for the multilayer neural network for four speakers.
Silicon nanophotonics show a lot of promise as the basic architecture for quantum information processing devices. This is particularly the case in relation to the scalability of such devices. During this talk I will review our simple theoretical model of a structure that we have identified as a ‘fundamental circuit element’ for linear optical quantum information processing in silicon nanophotonics. In particular, we have shown that, owing to an effect we call Passive Quantum Optical Feedback (PQOF), the topology of this circuit element allows for certain possible operational advantages, in addition to inherent scalability, not expected in bulk linear optics. I will emphasize the extension of our work to larger networks, including the Knill-Laflamme-Milburn (KLM) Controlled-Not (CNOT) gate and its important constituent, the so-called Nonlinear Sign (NS) shifter. Further, I will discuss our ongoing effort to design and optimize scalable networks that seem to have useful applications in quantum metrology and sensing. In developing the discussion, I will examine recent developments related to incorporation of losses and spectral properties in such a way as to generalize our simple, continuous-wave (cw) model of essentially lossless operation. I will also discuss on-chip generation and control of entangled photons within the nanophotonic material itself, especially as related to potentially useful applications in information processing.