This paper presents a novel pairwise classification framework for face recognition (FR). In the framework, a two-class (intra- and inter-personal) classification problem is considered and features are extracted using pairs of images. This approach makes it possible to incorporate prior knowledge through the selection of training image pairs and facilitates the application of the framework to tackle application areas such as facial aging. The non-linear empirical kernel map is used to reduce the dimensionality and the imbalance in the training sample set tackled by a novel training strategy. Experiments have been conducted using the FERET face database.format.
A semi-fragile watermarking algorithm for authenticating 2D engineering graphics based on log-polar coordinates mapping is proposed. Firstly, the coordinates of vertices of entities are mapped to the log-polar coordinate system to obtain the invariance of translation, scaling and rotation. Then the watermark is embedded in the mantissa of the real-valued log-polar coordinates via bit substitution. Theoretical analysis and experimental results show that the proposed algorithm is not only robust against incidental operations such as rotation, translation and scaling, but can also detect and locate malicious attacks such as entity modification, entity addition/deletion.
The use of multiple biometrics will work with greater efficiency if all the systems are capable of acquiring biometrics of adequate quality and processing them successfully. However if one or more of the biometrics fails, then the system has to rely on fewer or one biometric. If the individual biometrics are set to use low thresholds, the system maybe vulnerable to falsely accepting impostors. The motivation behind the proposed method is to provide an adaptive fusion platform where the software system can identify failures in certain algorithms and if necessary adapt the current rule to ignore these algorithms and adjust operating points accordingly. Results from experiments carried out on a multi-algorithmic and multi-biometric 3D and 2D database are presented to show that adopting such a system will result in an improvement in efficiency and verification rate.
Network Intrusion Detection Systems (NIDS) have gained substantial importance in today’s network security infrastructure. The performance of these devices in modern day traffic conditions is however found limited. It has been observed that the systems could hardly stand effective for the bandwidth of few hundred mega bits per second. Packet drop has been considered as the major bottleneck in the performance. We have identified a strong performance limitation of an open source Intrusion Detection System (IDS), Snort in [1, 2]. Snort was found dependent on host machine configuration. The response of Snort under heavy traffic conditions has opened a debate on its implementation and usage. We have developed the Smart Logic component to reduce the impact of packet drop in NIDS when subjected to heavy traffic volume. The proposed architecture utilizes packet capturing techniques applied at various processing stages shared between NIDS and packet handling applications. The designed architecture regains the lost traffic by a comparison between the analysed packets and the input stream using Smart Logic. The recaptured packets are then re-evaluated by a serialized IDS mechanism thus reducing impact of packet loss incurred in the routine implementation. The designed architecture has been implemented and tested on a scalable and sophisticated test bench replicating modern day network traffic. Our effort has shown noticeable improvement in the performance of Snort and has significantly improved its detection capacity.
This paper could be subtitled Are we teaching the next generation of computer criminals and internet terrorists"? This issue was raised by the Security Services as part of the collaborative network meeting in the area of IT Forensics and Data Analysis hosted by City University. These are valid concerns about the nature of material taught to computer science students in the area of security.The questions are also important ethical dilemmas for any professional working in the computer and internet security field. These are also applicable when discussing such security risks with the media, members of the public and even legislators. Information on vulnerabilities has to be presented so that it informs programmers and computer users about the areas of risk, but without providing recipes for them to use to conduct criminal activities or mischief themselves.The paper will look at several case studies from the curriculum at the University of Hull at both undergraduate and postgraduate level. Some specific problem areas of email forgery, security of the Windows operating system and exploitation of buffer overflows, and deception in online auctions, will be explored.
