Using feature selection and classification scheme for automating phishing email detection

Email has become the critical communication medium for most organizations. Unfortunately, email-born attacks in computer networks are causing considerable economic losses worldwide. Exiting phishing email blocking appliances have little effect in weeding out the vast majority of phishing emails. At the same time, online criminals are becoming more dangerous and sophisticated. Phishing emails are more active than ever before and putting the average computer user and organizations at risk of significant data, brand and financial loss. In this paper, we propose a hybrid feature selection approach based combination of content-based and behaviour-based. The approach could mine the attacker behaviour based on email header. On a publicly available test corpus, our hybrid features selection is able to achieve 94% accuracy rate.

Profiling phishing email based on clustering approach

In this paper, an approach for profiling email-born phishing activities is proposed. Profiling phishing activities are useful in determining the activity of an individual or a particular group of phishers. By generating profiles, phishing activities can be well understood and observed. Typically, work in the area of phishing is intended at detection of phishing emails, whereas we concentrate on profiling the phishing email. We formulate the profiling problem as a clustering problem using the various features in the phishing emails as feature vectors. Further, we generate profiles based on clustering predictions. These predictions are further utilized to generate complete profiles of these emails. The performance of the clustering algorithms at the earlier stage is crucial for the effectiveness of this model. We carried out an experimental evaluation to determine the performance of many classification algorithms by incorporating clustering approach in our model. Our proposed profiling email-born phishing algorithm (ProEP) demonstrates promising results with the RatioSize rules for selecting the optimal number of clusters.

Iterative development of Stand Up Australia : a multi-component intervention to reduce workplace sitting

Sitting, particularly in prolonged, unbroken bouts, is widespread within the office workplace, yet few interventions have addressed this newly-identified health risk behaviour. This paper describes the iterative development process and resulting intervention procedures for the Stand Up Australia research program focusing on a multi-component workplace intervention to reduce sitting time. The development of Stand Up Australia followed three phases. 1) Conceptualisation: Stand Up Australia was based on social cognitive theory and social ecological model components. These were operationalised via a taxonomy of intervention strategies and designed to target multiple levels of influence including: organisational structures (e.g. via management consultation), the physical work environment (via provision of height-adjustable workstations), and individual employees (e.g. via face-to-face coaching). 2) Formative research: Intervention components were separately tested for their feasibility and acceptability. 3) Pilot studies: Stand Up Comcare tested the integrated intervention elements in a controlled pilot study examining efficacy, feasibility and acceptability. Stand Up UQ examined the additional value of the organisational- and individual-level components over height-adjustable workstations only in a three-arm controlled trial. In both pilot studies, office workers’ sitting time was measured objectively using activPAL3 devices and the intervention was refined based on qualitative feedback from managers and employees. Results and feedback from participants and managers involved in the intervention development phases suggest high efficacy, acceptance, and feasibility of all intervention components. The final version of the Stand Up Australia intervention includes strategies at the organisational (senior management consultation, representatives consultation workshop, team champions, staff information and brainstorming session with information booklet, and supportive emails from managers to staff), environmental (height-adjustable workstations), and individual level (face-to-face coaching session and telephone support). Stand Up Australia is currently being evaluated in the context of a cluster-randomised controlled trial at the Department of Human Services (DHS) in Melbourne, Australia. Stand Up Australia is an evidence-guided and systematically developed workplace intervention targeting reductions in office workers’ sitting time.

Factors affecting acceptability of an email-based intervention to increase fruit and vegetable consumption

 Background: Fresh Facts is a 30-day email-delivered intervention designed to increase the fruit and vegetable consumption of Australian young adults. This study investigated the extent to which the program was acceptable to members of the target audience and examined the relationships between participant and intervention characteristics, attrition, effectiveness, and acceptability ratings. Methods: Young adults were randomised to two levels of message frequency: high-frequency (n = 102), low-frequency (n = 173). Individuals in the high-frequency group received daily emails while individuals in the low-frequency group received an email every 3 days. Results: Individuals in the high-frequency group were more likely to indicate that they received too many emails than individuals in the low-frequency group. No other differences in acceptability were observed. Baseline beliefs about fruit and vegetables were an important predictor of intervention acceptability. In turn, acceptability was associated with a number of indicators of intervention success, including change in fruit and vegetable consumption. Conclusions: The findings highlight the importance of considering the relationship between these intervention and participant factors and acceptability in intervention design and evaluation. Results support the ongoing use of email-based interventions to target fruit and vegetable consumption within young adults. However, the relationships between beliefs about fruit and vegetable consumption and acceptability suggest that this intervention may be differentially effective depending on individual's existing beliefs about fruit and vegetable consumption. As such, there is a pressing need to consider these factors in future research in order to minimize attrition and maximize intervention effectiveness when interventions are implemented outside of a research context.

An approach for profiling phishing activities

Phishing attacks continue unabated to plague Internet users and trick them into providing personal and confidential information to phishers. In this paper, an approach for email-born phishing detection based on profiling and clustering techniques is proposed. We formulate the profiling problem as a clustering problem using various features present in the phishing emails as feature vectors and generate profiles based on clustering predictions. These predictions are further utilized to generate complete profiles of the emails. We carried out extensive experimental analysis of the proposed approach in order to evaluate its effectiveness to various factors such as sensitivity to the type of data, number of data sizes and cluster sizes. We compared the performance of the proposed approach against the Modified Global Kmeans (MGKmeans) approach. The results show that the proposed approach is efficient as compared to the baseline approach. © 2014 Elsevier Ltd. All rights reserved.

Automatic generation of meta classifiers with large levels for distributed computing and networking

This paper is devoted to a case study of a new construction of classifiers. These classifiers are called automatically generated multi-level meta classifiers, AGMLMC. The construction combines diverse meta classifiers in a new way to create a unified system. This original construction can be generated automatically producing classifiers with large levels. Different meta classifiers are incorporated as low-level integral parts of another meta classifier at the top level. It is intended for the distributed computing and networking. The AGMLMC classifiers are unified classifiers with many parts that can operate in parallel. This make it easy to adopt them in distributed applications. This paper introduces new construction of classifiers and undertakes an experimental study of their performance. We look at a case study of their effectiveness in the special case of the detection and filtering of phishing emails. This is a possible important application area for such large and distributed classification systems. Our experiments investigate the effectiveness of combining diverse meta classifiers into one AGMLMC classifier in the case study of detection and filtering of phishing emails. The results show that new classifiers with large levels achieved better performance compared to the base classifiers and simple meta classifiers classifiers. This demonstrates that the new technique can be applied to increase the performance if diverse meta classifiers are included in the system.

Towards designing an email classification system using multi-view based semi-supervised learning

The goal of email classification is to classify user emails into spam and legitimate ones. Many supervised learning algorithms have been invented in this domain to accomplish the task, and these algorithms require a large number of labeled training data. However, data labeling is a labor intensive task and requires in-depth domain knowledge. Thus, only a very small proportion of the data can be labeled in practice. This bottleneck greatly degrades the effectiveness of supervised email classification systems. In order to address this problem, in this work, we first identify some critical issues regarding supervised machine learning-based email classification. Then we propose an effective classification model based on multi-view disagreement-based semi-supervised learning. The motivation behind the attempt of using multi-view and semi-supervised learning is that multi-view can provide richer information for classification, which is often ignored by literature, and semi-supervised learning supplies with the capability of coping with labeled and unlabeled data. In the evaluation, we demonstrate that the multi-view data can improve the email classification than using a single view data, and that the proposed model working with our algorithm can achieve better performance as compared to the existing similar algorithms.

Weight loss and attrition in overweight and obese young women during a 36- week internet-based lifestyle intervention

Background: Young women are at high risk of weight gain yet few studies have examined the long-term effectiveness of weight loss programs in this group. This study aimed to investigate the effects of a self-directed internet-based lifestyle program on body weight in young women.

Methods: Overweight or obese young women (BMI 33.4 ± 0.3 kg/m2, age 27.8 ± 0.3 years) were initially randomized to General lifestyle advice (G) or Structured lifestyle advice (S) via in-person and website support for 12 weeks (Phase I). After Phase I, all participants were supported through a self-directed internet-based program for 36 weeks (Phase II). The internet-based program included a structured hypocaloric diet, physical activity program, self-monitoring tools, peer group forum and monthly emails. Body weight, energy intake and physical activity were measured at week 0, week 12, week 24 and week 48. Adherence to self-regulatory behaviors was measured at week 48. Mixed model analyses were conducted to determine changes in body weight, energy intake and physical activity.

Results: A total of 203 overweight or obese young women commenced Phase I and 130 commenced Phase II. In Phase I, S group had significantly greater weight loss than G group (4.2 ± 0.6 kg vs 0.6 ± 0.3 kg, P<0.001). In Phase II, both groups had significant weight loss over time without significant group differences (-0.8 ± 1.1kg vs -0.8 ± 0.6, P>0.05). Forty-one percent (53/130) of the participants who commenced Phase II completed the internet-based intervention. Dropouts had a higher baseline BMI, were more likely to be married or in a de facto relationship, and more likely to have at least one child.

Conclusions: A self-directed internet-based program could be effective in providing support in maintaining weight loss on a structured lifestyle program in young women over 36 weeks. Further research is required to maintain engagement in young women who were married/in a de facto relationship or have children.

Database of Australian doctorates

Lists PhD theses created by Australian researchers within the period 1948-2006. Does not include professional doctorates.

Multilayer hybrid strategy for phishing email zero-day filtering

The cyber security threats from phishing emails have been growing buoyed by the capacity of their distributors to fine-tune their trickery and defeat previously known filtering techniques. The detection of novel phishing emails that had not appeared previously, also known as zero-day phishing emails, remains a particular challenge. This paper proposes a multilayer hybrid strategy (MHS) for zero-day filtering of phishing emails that appear during a separate time span by using training data collected previously during another time span. This strategy creates a large ensemble of classifiers and then applies a novel method for pruning the ensemble. The majority of known pruning algorithms belong to the following three categories: ranking based, clustering based, and optimization-based pruning. This paper introduces and investigates a multilayer hybrid pruning. Its application in MHS combines all three approaches in one scheme: ranking, clustering, and optimization. Furthermore, we carry out thorough empirical study of the performance of the MHS for the filtering of phishing emails. Our empirical study compares the performance of MHS strategy with other machine learning classifiers. The results of our empirical study demonstrate that MHS achieved the best outcomes and multilayer hybrid pruning performed better than other pruning techniques.