Jarrod Trevathan

Neural Network-based Handwritten Signature Verification

Handwritten signatures are considered as the most natural method of authenticating a person’s identity (compared to other biometric and cryptographic forms of authentication). The learning process inherent in Neural Networks (NN) can be applied to the process of verifying handwritten signatures that are electronically captured via a stylus. This paper presents a method for verifying handwritten signatures by using a NN architecture. Various static (e.g., height, slant, etc.) and dynamic (e.g., velocity, pen tip pressure, etc.) signature features are extracted and used to train the NN. Several Network topologies are tested and their accuracy is compared. The resulting system performs reasonably well with an overall error rate of 3:3% being reported for the best case.

Detecting Collusive Shill Bidding

Shill bidding is where spurious bids are introduced into an auction to drive up the final price for the seller, thereby defrauding legitimate bidders. Trevathan and Read presented an algorithm to detect the presence of shill bidding in online auctions. The algorithm observes bidding patterns over a series of auctions, and gives each bidder a shill score to indicate the likelihood that they are engaging in shill behaviour. While the algorithm is able to accurately identify those with suspicious behaviour, it is designed for the instance where there is only one shill bidder. However, there are situations where there may be two or more shill bidders working in collusion with each other. Colluding shill bidders are able to engage in more sophisticated strategies that are harder to detect. This paper proposes a method for detecting colluding shill bidders, which is referred to as the collusion score. The collusion score, either detects a colluding group, or forces the colluders to act individually like a single shill, in which case they are detected by the shill score algorithm. The collusion score has been tested on simulated auction data and is able to successfully identify colluding shill bidders

SEMAT — The Next Generation of Inexpensive Marine Environmental Monitoring and Measurement Systems

There is an increasing need for environmental measurement systems to further science and thereby lead to improved policies for sustainable management. Marine environments are particularly hostile and extremely difficult for deploying sensitive measurement systems. As a consequence the need for data is greatest in marine environments, particularly in the developing economies/regions. Expense is typically the most significant limiting factor in the number of measurement systems that can be deployed, although technical complexity and the consequent high level of technical skill required for deployment and servicing runs a close second. This paper describes the Smart Environmental Monitoring and Analysis Technologies (SEMAT) project and the present development of the SEMAT technology. SEMAT is a “smart” wireless sensor network that uses a commodity-based approach for selecting technologies most appropriate to the scientifically driven marine research and monitoring domain/field. This approach allows for significantly cheaper environmental observation systems that cover a larger geographical area and can therefore collect more representative data. We describe SEMATs goals, which include: (1) The ability to adapt and evolve; (2) Underwater wireless communications; (3) Short-range wireless power transmission; (4) Plug and play components; (5) Minimal deployment expertise; (6) Near real-time analysis tools; and (7) Intelligent sensors. This paper illustrates how the capacity of the system has been improved over three iterations towards realising these goals. The result is an inexpensive and flexible system that is ideal for short-term deployments in shallow coastal and other aquatic environments.

An Anonymous and Secure Continuous Double Auction Scheme

A Continuous Double Auction (CDA) allows many buyers and sellers to continuously submit bids for the purchase and sale of a commodity (e.g., online share trading). Protocols protecting privacy in this type of powerful market mechanism are essential. However, until recently the security of CDAs has been given limited coverage. This paper describes a new scheme for conducting an anonymous and secure CDA. We show that any existing secure group signature scheme can be used to implement a CDA which has the following characteristics: unforgeability, anonymity, unlinkability, exculpability, coalitionresistance, verifiability, robustness and traceability. Furthermore, bidders can be added to and removed from the auction without affecting the process of the auction. Our scheme is more flexible than the only existing secure CDA scheme, which in contrast provides only a limited subset of these characteristics.

A Simple Shill Bidding Agent

Shill bidding is where fake bids are introduced into an auction to drive up the final price for the seller, thereby defrauding legitimate bidders. Although shill bidding is strictly forbidden in online auctions such as eBay, it is still a major problem. This paper presents a software bidding agent that follows a shill bidding strategy. The malicious bidding agent was constructed to aid in developing shill detection techniques. The agent incrementally increases an auctions price, forcing legitimate bidders to submit higher bids in order to win the item. The agent ceases bidding when the desired profit from shilling has been attained, or in the case that it is too risky to continue bidding without winning the auction. The agents ability to inflate the price has been tested in a simulated marketplace and experimental results are presented. This is the first documented bidding agent that perpetrates auction fraud. We do not condone the use of the agent outside the scope of this research

RAS: a system for supporting research in online auctions

Online auctioning is unparalleled as rhe fastest growing exchange medium to emerge from electronic commerce technology. Buyers and sellers located around the world now auction various items from the latest DVD to rare collectibles. eBay and uBid are among the most successful and popular of the commercial online auctioneers. They use an auctioning process based on a type of auction referred to as an English auction. In an English auction. bidders outbid each other for an item. The winner is the bidder with the highest bid.

Handwritten Signature Verification Using Complementary Statistical Models

This paper describes a system for performing handwritten signature verification using complementary statistical models. The system analyses both the static features of a signature (e.g., shape, slant, size), and its dynamic features (e.g., velocity, pen-tip pressure, timing) to form a judgment about the signer’s identity. This approach’s novelty lies in combining output from existing Neural Network and Hidden Markov Model based signature verification systems to improve the robustness of any specific approach used alone. The system performs reasonably well and achieves an overall error rate of 2:1% in the best case. The results of several other experiments are also presented including using less reference signatures, allowing multiple signing attempts, zero- effort forgery attempts, providing visual feedback, and signing a password rather than a signature.

Markov Model-Based Handwritten Signature Verification

Biometric security devices are now permeating all facets of modern society. All manner of items including passports, drivers licences and laptops now incorporate some form of biometric data and/or authentication device. As handwritten signatures have long been considered the most natural method of verifying ones identity, it makes sense that pervasive computing environments try to capitalise on the use of automated Handwritten Signature Verification systems (HSV). This paper presents a HSV system that is based on a Hidden Markov Model (HMM) approach to representing and verifying the hand signature data. HMMs are naturally suited to modelling flowing entities such as signatures and speech. The resulting HSV system performs reasonably well with an overall error rate of 3.5% being reported in the best case experimental analysis.

Investigating Shill Bidding Behaviour Involving Colluding Bidders

Shill bidding is where spurious bids are introduced into an auction to drive up the final price for the seller, thereby defrauding legitimate bidders. Trevathan and Read presented an algorithm to detect the presence of shill bidding in online auctions. The algorithm observes bidding patterns over a series of auctions, and gives each bidder a shill score to indicate the likelihood that they are engaging in shill behaviour. While the algorithm is able to accurately identify those with suspicious behaviour, it is designed for the instance where there is only one shill bidder. However, there are situations where there may be two or more shill bidders working in collusion with each other. Colluding shill bidders are able to engage in more sophisticated strategies that are harder to detect. This paper proposes a method for detecting colluding shill bidders, which is referred to as the collusion score. The collusion score, either detects a colluding group, or forces the colluders to act individually like a single shill, in which case they are detected by the shill score algorithm. The collusion score has been tested on simulated auction data and is able to successfully identify colluding shill bidders.

Developing low-cost intelligent wireless sensor networks for aquatic environments

Aquatic environments are extremely difficult for developing, deploying, and maintaining wireless sensor networks. Networks deployed in aquatic settings face multiple challenges, such as marine fowling of equipment, limited power supply, communications difficulties, and restricted accessibility for maintaining and updating sensor nodes. The SEMAT project is an initiative to create “smart”, low-cost, heterogeneous wireless sensor networks, tailored to alleviating the aforementioned constraints. Networks can be instantly deployable with minimal setup overheads and can utilise equipment from multiple vendors. This paper presents our experiences with developing the initial technologies to establish SEMAT for field tests. We present the design methodology and challenges faced for creating a marinebased heterogeneous wireless sensor network platform. The result is a low cost solution, with sufficient accuracy for undertaking a study into the factors contributing to Lyngbya algae blooms in Deception Bay, Queensland. The platform builds a case for the merits of the final SEMAT system, as ultimately many of the software and basic hardware challenges for future aquatic deployments have been overcome. This is significant as it allows researchers to focus on the area under study, rather than the specifics of setting up and managing the network.