Improvement of DDoS attack detection and web access anonymity

The thesis has covered a range of algorithms that help to improve the security of web services. The research focused on the problems of DDoS attack and traffic analysis attack against service availability and information privacy respectively. Finally, this research significantly advantaged DDoS attack detection and web access anonymity.

Detection of setting and subject information in documentary video

Interpretation of video information is a difficult task for computer vision and machine intelligence. In this paper we examine the utility of a non-image based source of information about video contents, namely the shot list, and study its use in aiding image interpretation. We show how the shot list may be analysed to produce a simple summary of the 'who and where' of a documentary or interview video. In order to detect the subject of a video we use the notion of a 'shot syntax' of a particular genre to isolate actual interview sections.

Efficient algorithms for subwindow search in object detection and localization

Recently, a simple yet powerful branch-and-bound method called Efficient Subwindow Search (ESS) was developed to speed up sliding window search in object detection. A major drawback of ESS is that its computational complexity varies widely from O(n²) to O(n⁴) for n × n matrices. Our experimental experience shows that the ESS's performance is highly related to the optimal confidence levels which indicate the probability of the object's presence. In particular, when the object is not in the image, the optimal subwindow scores low and ESS may take a large amount of iterations to converge to the optimal solution and so perform very slow. Addressing this problem, we present two significantly faster methods based on the linear-time Kadane's Algorithm for 1D maximum subarray search. The first algorithm is a novel, computationally superior branchand- bound method where the worst case complexity is reduced to O(n³). Experiments on the PASCAL VOC 2006 data set demonstrate that this method is significantly and consistently faster (approximately 30 times faster on average) than the original ESS. Our second algorithm is an approximate algorithm based on alternating search, whose computational complexity is typically O(n²). Experiments shows that (on average) it is 30 times faster again than our first algorithm, or 900 times faster than ESS. It is thus wellsuited for real time object detection.

Narrative structure detection through audio pace

We use the concept of film pace, expressed through the audio, to analyse the broad level narrative structure of film. The narrative structure is divided into visual narration, action sections, and audio narration, plot development sections. We hypothesise, that changes in the narrative structure signal a change in audio content, which is reflected by a change in audio pace. We test this hypothesis using a number of audio feature functions, that reflect the audio pace, to detect changes in narrative structure for 8 films of varying genres. The properties of the energy were then used to determine the. audio pace feature corresponding to the narrative, structure for each film analysed. The method was successful in determining the narrative structure for 1 of the films, achieving an overall precision of 76.4% and recall of 80.3%, We map the properties of the speech and energy of film audio to the higher level semantic concept of audio pace. The audio pace was in turn applied to a higher level semantic analysis of the structure of film.

Injection, detection and repair of aesthetics in home movies

This paper details the design of an algorithm for automatically manipulating the important aesthetic element of video, visual tempo. Automatic injection, detection and repair of such aesthetic elements, it is argued, is vital to the next generation of amateur multimedia authoring tools. We evaluate the performance of the algorithm on a battery of synthetic data and demonstrate its ability to return the visual tempo of the final media a considerable degree closer to the target signal. The novelty of this work lies chiefly in the systematic manipulation of this high level aesthetic element of video.

A Grobner-Shirshov algorithm for applications in internet security

The design of multiple classification and clustering systems for the detection of malware is an important problem in internet security. Grobner-Shirshov bases have been used recently by Dazeley et al. [15] to develop an algorithm for constructions with certain restrictions on the sandwich-matrices. We develop a new Grobner Shirshov algorithm which applies to a larger variety of constructions based on combinatorial Rees matrix semigroups without any restrictions on the sandwich matrices.

K-Complex Detection Using a Hybrid-Synergic Machine Learning Method

Sleep stage identification is the first step in modern sleep disorder diagnostics process. K-complex is an indicator for the sleep stage 2. However, due to the ambiguity of the translation of the medical standards into a computer-based procedure, reliability of automated K-complex detection from the EEG wave is still far from expectation. More specifically, there are some significant barriers to the research of automatic K-complex detection. First, there is no adequate description of K-complex that makes it difficult to develop automatic detection algorithm. Second, human experts only provided the label for whether a whole EEG segment contains K-complex or not, rather than individual labels for each subsegment. These barriers render most pattern recognition algorithms inapplicable in detecting K-complex. In this paper, we attempt to address these two challenges, by designing a new feature extraction method that can transform visual features of the EEG wave with any length into mathematical representation and proposing a hybrid-synergic machine learning method to build a K-complex classifier. The tenfold cross-validation results indicate that both the accuracy and the precision of this proposed model are at least as good as a human expert in K-complex detection.

A hybrid neural classifier for dimensionality reduction and data visualization and its application to fault detection and classification of induction motors

In this paper, a hybrid neural classifier combining the auto-encoder neural network and the Lattice Vector Quantization (LVQ) model is described. The auto-encoder network is used for dimensionality reduction by projecting high dimensional data into the 2D space. The LVQ model is used for data visualization by forming and adapting the granularity of a data map. The mapped data are employed to predict the target classes of new data samples. To improve classification accuracy, a majority voting scheme is adopted by the hybrid classifier. To demonstrate the applicability of the hybrid classifier, a series of experiments using simulated and real fault data from induction motors is conducted. The results show that the hybrid classifier is able to outperform the Multi-Layer Perceptron neural network, and to produce very good classification accuracy rates for various fault conditions of induction motors.

Authenticating the identity of computer users with typing biometrics and the fuzzy min-max neural network

In this paper, typing biometrics is applied as an additional security measure to the password-based or Personal Identification Number (PIN)-based systems to authenticate the identity of computer users. In particular, keystroke pressure and latency signals are analyzed using the Fuzzy Min-Max (FMM) neural network for authentication purposes. A special pressure-sensitive keyboard is designed to collect keystroke pressure signals, in addition to the latency signals, from computer users when they type their passwords. Based on the keystroke pressure and latency signals, the FMM network is employed to classify the computer users into two categories, i.e., genuine users or impostors. To assess the effectiveness of the proposed approach, two sets of experiments are conducted, and the results are compared with those from statistical methods and neural network models. The experimental outcomes positively demonstrate the potentials of using typing biometrics and the FMM network to provide an additional security layer for the current password-based or PIN-based methods in authenticating the identity of computer users.

Visual mouse : SIFT detection and PCA recognition

The paper presents the Visual Mouse (VM), a novel and simple system for interaction with displays via hand gestures. Our method includes detecting bare hands using the fast SIFT (Scale-Invariant Feature Transform) algorithm saving long training time of the Adaboost algorithm, tracking hands based on the CAMShift algorithm, recognizing hand gestures in cluttered background via Principle Components Analysis (PCA) without extracting clear-cut hand contour, and defining simple and robustly interpretable vocabularies of hand gestures, which are subsequently used to control a computer mouse. The system provides a fast and simple interaction experience without the need for more expensive hardware and software.

Detecting and mitigating HX-DoS attacks against cloud web services

Cyber-Physical Systems allow for the interaction of the cyber world and physical worlds using as a central service called Cloud Web Services. Cloud Web Services can sit well within three models of Cyber- Physical Systems, Software-as-a-Service (SaaS), Platform-as-a-Service (PaaS), and Infrastructure-as-a- Service (IaaS). With any Cyber-Physical system use Cloud Web Services it inherits a security problem, the HX-DoS attack. HX-DoS attack is a combination of HTTP and XML messages that are intentionally sent to flood and destroy the communication channel of the cloud service provider. The relevance of this research is that TCP/IP flood attacks are a common problem and a lot of research to mitigate them has previously been discussed. But HTTP denial of service and XML denial of service problem has only been addressed in a few papers. In this paper, we get closer to closing this gap on this problem with our new defence system called Pre- Decision, Advance Decision, Learning System (ENDER). In our previous experiments using our Cloud Protector, we were successful at detecting and mitigate 91% with a 9% false positive of HX-DoS attack traffic. In this paper, ENDER was able to improve upon this result by being trained and tested on the same data, but with a greater result of 99% detection and 1% false positive.

Drugs, ships and containers : how anti-terrorism benefits shipping security

Using ships to transport illicit drugs is not new; nor is the practice of concealing them
in shipping containers decreasing – or is it? This article questions whether recent container security initiatives created to stop terrorism have also achieved a decrease in the use of containers for smuggling illicit drugs. Or, are these maritime security regimes creating a false sense of achievement, being too limited in scope to be truly useful in this secondary role? Logically, improved detection of illicit drugs in containers shipped by sea is more likely when port personnel are better trained, x-ray scanners installed, port fencing improved and official collaboration encouraged. However, since the number of containers being electronically screened and physically searched has only marginally improved, the question is, is it enough?

Keynote : Detection of and defense against distributed denial-of-service (DDoS) attacks

Distributed denial-of-service (DDoS) attacks typically exhaust bandwidth, processing capacity, or memory of a targeted machine, service or network. Despite enormous efforts in combating DDoS attacks in the past decade, DDoS attacks are still a serious threat to the security of cyberspace. In this talk I shall outline the recent efforts of my research group in detection of and defence against DDoS attacks. In particular, this talk will concentrate on the following three critical issues related to DDoS attacks: (1) Traceback of DDoS attacks; (2) Detection of low-rate DDoS attacks; and (3) Discriminating DDoS attacks from flash crowds.

Solar greenhouse technology for food security : a case study from Humla District, NW Nepal

Food security is a significant issue for many people who live in remote mountain areas around the world. Most of these people are also poor because of the lack of opportunity to earn cash. Malnutrition is common because the harsh climate restricts production and access to fresh food. Simple conventional greenhouses can provide some improvement of growing conditions, but the benefits are limited because of the high heat losses from these structures. Solar greenhouses, however, which are designed to store some of the heat generated within the structure can overcome these limitations. This article describes the experiences of a nongovernmental organization that has been introducing community and family-owned solar greenhouses into the remote villages of Humla, a mountainous district of northwest Nepal prone to food insecurity. The overall result has been positive. Family-owned greenhouses, which avoid the issues of community ownership and operation, have been more successful. A validated computer model based on the first solar greenhouse has been used to predict the thermal performance of a new family-sized design. Training and education are vital to the success of solar greenhouse technology in remote mountain areas.