Configuring privacy-preserving methods for real-world datasets remains a significant challenge, as optimal parameters vary substantially across different data characteristics and use cases, requiring careful balancing between privacy protection and data utility. Current approaches rely heavily on manual parameter tuning, leading to inefficient and potentially suboptimal privacy-utility trade-offs. To address this critical gap, we present a novel framework that automatically assesses privacypreserving techniques across diverse datasets to set them at the right working spots. Our framework employs statistical analysis to narrow the parameter search space, dramatically reducing the computational overhead typically associated with finding optimal privacy configurations while maintaining high utility. The framework enables data scientists to rapidly identify optimal privacy-utility trade-offs for any privacy-preserving method. We demonstrate the framework's effectiveness by evaluating Differential Privacy (DP) and K-Anonymity (KA) methods on a wide range of input data, i.e., bank, disease, and oil well datasets. Through our experimentation, we observed that DP achieves optimal performance at moderate privacy budgets$(\epsilon$values between 0.01 and 0.0358), while KA's effectiveness varies with dataset characteristics, favoring lower$k$values for smaller datasets and higher$k$values for larger ones.

Connected and Autonomous Vehicles (CAVs) rely on the Controller Area Network (CAN) bus for critical communications but lack inherent security mechanisms, making them vulnerable to both Denial of Service (DoS) attacks and False Data Injection (FDI) attacks. This paper introduces a Trust-aware Federated Learning-Based Intrusion Detection System (Trustaware FL-IDS) framework that addresses these vulnerabilities while preserving data privacy and minimizing communication overhead. The core innovation is a dynamic trust-aware aggregation mechanism that assigns weights to client contributions based on validation accuracy, effectively mitigating the impact of compromised nodes. Extensive evaluation on both public CAN bus datasets and real-world autonomous vehicle data demonstrates that our approach significantly outperforms centralized IDS implementations, achieving up to $100 \%$ recovery rates against data poisoning attacks with $40 \%$ label manipulation. Notably, our analysis reveals that larger client networks ($\mathbf{1 0 0}$ vs. $\mathbf{1 0}$ clients) provide inherently stronger defenses and that label flip intensity has a greater impact on system performance than the proportion of compromised clients. The proposed framework offers a scalable, lightweight solution for real-time intrusion detection in resource-constrained vehicular environments, applicable in both urban and rural settings.

This paper presents an augmenting path based online max-flow algorithm. The proposed algorithm handles graph changes in chunk manner, updating residual graph in response to edge capacity increase, decrease, edge/node adding and removal. All possible graph changes are abstracted into two key graph changes, which are capacity decrease and in- crease. For capacity decrease, we release the occupied capacity by cycle cancellation and path de-augmentation to enable the capacity decrease. For capacity increase, we augment all s-t paths newly formed to update the current max-flow model. The theoretical guarantee of our algorithm is that online max- flow is always equal to batch retraining. Experiments show the deterministic computational cost save (i.e., gain) of our algorithm w.r.t batch retraining in handling graph edge adding.

Authentication methods based on some human traits, including fingerprint, face, iris, and palmprint, have been developed significantly, and currently, they are mature enough which have been reliably considered for person identification purposes. Recently, as a new research area, few methods based on non-facial skin features such as vein patterns have been developed. This extended abstract briefly explores some key features of biometric traits whereas vein pattern recognition is also outlined.

This paper proposes Copy-On-Risk (COR) honeypot solution and implementation. Our prototype COR-Honeypot defends against attacks by creating on demand a personalized honeypot by cloning the victim and isolating the attack to the newly created honeypot. We measure the effectiveness of COR-Honeypot on resource usage and similarity of personalized honeypot to the victim. Results over different configurations of COR-Honeypot have demonstrated the benefits of the proposed solution.

Comparable corpora contain significant quantities of useful data for Natural Language Processing tasks, especially in the area of Machine Translation. They are mainly the source of parallel text fragments. This paper investigates how to effectively extract bilingual texts from comparable corpora relying on a small-size parallel training corpus. We propose a new technique to filter non parallel articles in Wikipedia based on Zipfian frequency distribution. We also use the SVM approach to find parallel chunks of text in a candidate comparable document. In our approach we use a parallel corpus to generate the required features for the training step. The evaluations of generated bilingual texts are promising.

Malware is an international software disease. Research shows that the effect of malware is becoming chronic. To protect against malware detectors are fundamental to the industry. The effectiveness of such detectors depends on the technology used. Therefore, it is paramount that the advantages and disadvantages of each type of technology are scrutinized analytically. This study's aim is to scrutinize existing publications on this subject and to follow the trend that has taken place in the advancement and development with reference to the amount of information and sources of such literature. Many of the malware programs are huge and complicated and it is not easy to comprehend the details. Dissemination of malware information among users of the Internet and also training them to correctly use anti-malware products are crucial to protecting users from the malware onslaught. This paper will provide an exhaustive bibliography of methods to assist in combating malware.

There has been an exponential increase in the usage of the internet, particularly among students since the introduction of e-learning and Bring Your Own Device (BYO) initiatives into the education system. In New Zealand the percentage of the population using the internet is now 93.8% and this increase in internet usage has increased the risk of cybersecurity attacks. This makes it necessary to provide awareness and education on cybersecurity to students who are potential targets for exploitation. However, to provide this awareness it is necessary to understand what their current knowledge on cybersecurity is which forms the basis of this paper. This paper presents the results of a survey conducted on internet usage and cybersecurity awareness among three age groups between 8 years and 21 years. A questionnaire consisting of various questions on internet usage and cybersecurity concepts was prepared. For this survey, we considered both computers (desktops & laptops) and mobile devices (tablets & smartphones). The results of the survey showed that cybersecurity awareness among the surveyed students was generally low with the lowest level in the 8-12-year age group. The students of 8-12 age group were able to answer only 19% of survey questions. Furthermore, most of the students were not familiar with common cybersecurity terms and did not demonstrate enough awareness of common threats such as phishing. The results further show that the majority of the students were not aware of cybersecurity tools for tablets and smartphones which are frequently used devices for BYOD. The key contribution of this paper is to emphasise the necessity to create cybersecurity awareness among students.

Max-flow has been adopted for semi-supervised data modelling, yet existing algorithms were derived only for the learning from static data. This paper proposes an online max-flow algorithm for the semi-supervised learning from data streams. Consider a graph learned from labelled and unlabelled data, and the graph being updated dynamically for accommodating online data adding and retiring. In learning from the resulting non stationary graph, we augment and de-augment paths to update max-flow with a theoretical guarantee that the updated max-flow equals to that from batch retraining. For classification, we compute min-cut over current max-flow, so that minimized number of similar sample pairs are classified into distinct classes. Empirical evaluation on real-world data reveals that our algorithm outperforms state-of-the-art stream classification algorithms.

Agent-oriented techniques are being increasingly used in a range of networking security applications. In this paper, we introduce FNTAE, a Federated Network Traffic Analysis Engine for real-time network intrusion detection. In FNTAE, each analysis engine is powered with an incremental learning agent, for capturing attack signatures in real-time, so that the abnormal traffics resulting from the new attacks are detected as soon as they occur. Owing to the effective knowledge sharing among multiple analysis engines, the integrated engine is theoretically guaranteed performing more effective than a centralized analysis system. We deployed and tested FNTAE in a real world network environment. The results demonstrate that FNTAE is a promising solution to improving system security through the identification of malicious network traffic.

This article proposes a novel algorithm to improve the lifetime of a wireless sensor network. This algorithm employs swarm intelligence algorithms in conjunction with compressive sensing theory to build up the routing trees and to decrease the communication rate. The main contribution of this article is to extend swarm intelligence algorithms to build a routing tree in such a way that it can be utilized to maximize efficiency, thereby rectifying the delay problem of compressive sensing theory and improving the network lifetime. In addition, our approach offers accurate data recovery from small amounts of compressed data. Simulation results show that our approach can effectively extend the network lifetime of a large‐scale wireless sensor network.

Machine learning requires sufficient and reliable data to enhance the prediction performance. However, environmental data sometimes is short and/or contains missing data. Often existing prediction models built on machine learning fail to predict environmental problems accurately. We argue that spatial domain data can be used to facilitate the training of temporal prediction model. This paper formulates mathematically a spatial data aided incremental support vector regression (SalncSVR) for spatio-temporal PM2.5prediction. We conduct spatio-temporal PM2.5prediction over 13 monitoring stations in Auckland New Zealand, and compare the proposed SalncSVR with a pure temporal IncSVR prediction.

Business-to-Consumer (B2C) e-commerce is popular because of its convenience, speed and price. Although there has been intense debate about quality dimensions of e-commerce websites, more research is needed to find a well-established measurement. This empirical study identifies a set of measurements with 10 factors and their corresponding dimensions, including software development attributes based on the literature and the qualitative and quantitative data gathered from four different stakeholders. The survey results suggest that security, smooth transaction processes and smooth shopping processes are the most important concerns for online shoppers. The IS success model checking suggests that the proposed measurements are comprehensive. This work is compared with the customized ISO 9126 quality model.

Training data in real world is often presented in random chunks. Yet existing sequential Incremental IDR/QR LDA (s-QR/IncLDA) can only process data one sample after another. This paper proposes a constructive chunk Incremental IDR/QR LDA (c-QR/IncLDA) for multiple data samples incremental learning. Given a chunk of s samples for incremental learning, the proposed c-QR/IncLDA increments current discriminant model Ω, by implementing computation on the compressed the residue matrix Δ ϵ Rd×n, instead of the entire incoming data chunk X ϵ Rd×s, where η ≤ s holds. Meanwhile, we derive a more accurate reduced within-class scatter matrix W to minimize the discriminative information loss at every incremental learning cycle. It is noted that the computational complexity of c-QR/IncLDA can be more expensive than s-QR/IncLDA for single sample processing. However, for multiple samples processing, the computational efficiency of c-QR/IncLDA deterministically surpasses s-QR/IncLDA when the chunk size is large, i.e., s ≫ η holds. Moreover, experiments evaluation shows that the proposed c-QR/IncLDA can achieve an accuracy level that is competitive to batch QR/LDA and is consistently higher than s-QR/IncLDA.

Different from traditional P2P systems, individuals nodes of a Federated Service Providing (FSP) system play a more active role by offering a variety of domain-specific services. The service provision control (SPC) problem is an important problem of the FSP system and will be tackled in this paper within a stochastic optimization framework through several steps. The first step focuses on using stochastic differential equations (SDEs) to model and analyze the dynamic evolution of the service demand. Driven by the SDE model, expected future performance of a FSP system is analytically evaluated in the second step. Step three utilizes the differential evolution (DE) algorithm to identify near-optimal service-providing policies for each node. The service subscription protocol is further proposed in step four to help every node adjust its local policy in accordance with the services provided by other nodes. The four steps together implement a complete solution of the SPC problem and will be called the SDE-based service-provision control (SSPC) mechanism in this paper. Experimental evaluation of the mechanism has been reported in the paper. The results show that our approach is effective in tackling the SPC problem and may be therefore suitable for many practical applications.

Linear Proximal Support Vector Machines (LPSVM), like decision trees, classic SVM, etc. are originally not equipped to handle drifting data streams that exhibit high and varying degrees of class imbalance. For online classification of data streams with imbalanced class distribution, we propose an incremental LPSVM termed DCIL-IncLPSVM that has robust learning performance under class imbalance. In doing so, we simplify a weighted LPSVM, which is computationally not renewable, as several core matrices multiplying two simple weight coefficients. When data addition and/or retirement occurs, the proposed DCIL-IncLPSVM accommodates current class imbalance by a simple matrix and coefficient updating, meanwhile ensures no discriminative information lost throughout the learning process. Experiments on benchmark datasets indicate that the proposed DCIL-IncLPSVM outperforms batch SVM and LPSVM in terms of F-measure, relative sensitivity and G-mean metrics. Moreover, our application to online face membership authentication shows that the proposed DCIL-IncLPSVM remains effective in the presence of highly dynamic class imbalance, which usually poses serious problems to classic incremental SVM (IncSVM) and incremental LPSVM (IncLPSVM).

P2P-like applications are quickly gaining popularity in the Internet. Such applications are commonly modeled as graphs with nodes and edges. Usually nodes represent running processes that exchange information with each other through communication channels as represented by the edges. They often need to autonomously determine their suitable working mode or local status for the purpose of improving performance, reducing operation cost, or achieving system-level design goals. In order to achieve this objective, the concept of status configuration is introduced in this article and a mathematical correspondence is further established between status configuration and an optimization index ( OI ), which serves as a unified abstraction of any system design goals. Guided by this correspondence and inspired by the cross-entropy algorithm, a cross-entropy-driven self-organization mechanism (CESM) is proposed in this article. CESM exhibits the self-organization property since desirable status configurations that lead to high OI values will quickly emerge from purely localized interactions. Both theoretical and experimental analysis have been performed. The results strongly indicate that CESM is a simple yet effective technique which is potentially suitable for many P2P-like applications.

In this paper we introduce a novel technique for modeling and recognizing gesture signals in 2D space. This technique is based on measuring the direction of the gradient of the movement trajectory as features of the gesture signal. Each gesture signal is represented as a time series of gradient angle values. These features are classified by applying a given classification method. In this article we compared the accuracy of a feed forward Artificial Neural Network with a Support Vector Machine using a radial kernel. The comparison was based on the recorded data of 13 gesture signals as training and testing data. The average accuracy of the ANN and SVM were 98.27% and 96.34% respectively. The false detection ratio was 3.83% for ANN and 8.45% for SVM, which suggests the ANN is more suitable for gesture signal recognition.

Intelligent tutoring systems (ITS) provide individualized instruction. They offer many advantages over the traditional classroom scenario: they are always available, nonjudgmental and provide tailored feedback resulting in increased and effective learning. However, they are still not as effective as one-on-one human tutoring. The next generation of intelligent tutors is expected to be able to take into account the cognitive and emotional state of students. We present a proposed contribution of affect to student modeling, and reports on the progress made in the development of a facial expression analysis component for intelligent tutoring systems.