Describing user activity plays an essential role in ambient intelligence. In this work, we review different methods for human activity recognition, classified as data-driven and knowledge-based techniques. We focus on context ontologies whose ultimate goal is the tracking of human behavior. After studying upper and domain ontologies, both useful for human activity representation and inference, we establish an evaluation criterion to assess the suitability of the different candidate ontologies for this purpose. As a result, any missing features, which are relevant for modeling daily human behaviors, are identified as future challenges.

https://dl.acm.org/doi/pdf/10.1145/2523819

A survey on ontologies for human behavior recognition

While there have been extensive studies of denial of service (DoS) attacks and DDoS attack mitigation, such attacks remain challenging to mitigate. For example, Low-Rate DDoS (LR-DDoS) attacks are known to be difficult to detect, particularly in a software-defined network (SDN). Hence, in this paper we present a flexible modular architecture that allows the identification and mitigation of LR-DDoS attacks in SDN settings. Specifically, we train the intrusion detection system (IDS) in our architecture using six machine learning (ML) models (i.e., J48, Random Tree, REP Tree, Random Forest, Multi-Layer Perceptron (MLP), and Support Vector Machines (SVM)) and evaluate their performance using the Canadian Institute of Cybersecurity (CIC) DoS dataset. The findings from the evaluation demonstrate that our approach achieves a detection rate of 95%, despite the difficulty in detecting LR-DoS attacks. We also remark that in our deployment, we use the open network operating system (ONOS) controller running on Mininet virtual machine in order for our simulated environment to be as close to real-world production networks as possible. In our testing topology, the intrusion prevention detection system mitigates all attacks previously detected by the IDS system. This demonstrates the utility of our architecture in identifying and mitigating LR-DDoS attacks.

/pdf/a-flexible-sdn-based-architecture-for-identifying-and-2h3oonc43x.pdf

A Flexible SDN-Based Architecture for Identifying and Mitigating Low-Rate DDoS Attacks Using Machine Learning

This chapter contains sections titled: Introduction, An Overview of Service Discovery Protocols, Multiprotocol Service Discovery, Context-Aware Service Discovery for Pervasive Environments, Conclusion, Acknowledgment, Notes, References

Service Discovery in Pervasive Computing Environments

Ransomware is a type of advanced malware that has spread rapidly in recent years, causing significant financial losses for a wide range of victims, including organizations, healthcare facilities, and individuals. Modern host-based detection methods require the host to be infected first in order to identify anomalies and detect the malware. By the time of infection, it can be too late as some of the system's assets would have been already exfiltrated or encrypted by the malware. Conversely, the network-based methods can be effective in detecting ransomware attacks, as most ransomware families try to connect to command and control servers before their harmful payloads are executed. Therefore, a careful analysis of ransomware network traffic can be one of the key means for early detection. This paper demonstrates a comprehensive behavioral analysis of crypto ransomware network activities, taking Locky, one of the most serious families, as a case study. A dedicated testbed was built, and a set of valuable and informative network features were extracted and classified into multiple types. A network-based intrusion detection system was implemented, employing two independent classifiers working in parallel on different levels: packet and flow levels. The experimental evaluation of the proposed detection system demonstrates that it offers high detection accuracy, low false positive rate, valid extracted features, and is highly effective in tracking ransomware network activities.

/pdf/a-multi-classifier-network-based-crypto-ransomware-detection-1z15x3b0h0.pdf

A Multi-Classifier Network-Based Crypto Ransomware Detection System: A Case Study of Locky Ransomware

Background: The greatest potential to reduce the burden of stroke is by primary prevention of first-ever stroke, which constitutes three quarters of all stroke. In addition to population-wide prevention strategies (the 'mass' approach), the 'high risk' approach aims to identify individuals at risk of stroke and to modify their risk factors, and risk, accordingly. Current methods of assessing and modifying stroke risk are difficult to access and implement by the general population, amongst whom most future strokes will arise. To help reduce the burden of stroke on individuals and the population a new app, the Stroke RiskometerTM, has been developed. We aim to explore the validity of the app for predicting the risk of stroke compared with current best methods. Methods: 752 stroke outcomes from a sample of 9501 individuals across three countries (New Zealand, Russia and the Netherlands) were utilized to investigate the performance of a novel stroke risk prediction tool algorithm (Stroke RiskometerTM) compared with two established stroke risk score prediction algorithms (Framingham Stroke Risk Score [FSRS] and QStroke). We calculated the receiver operating characteristics (ROC) curves and area under the ROC curve (AUROC) with 95% confidence intervals, Harrels C-statistic and D-statistics for measure of discrimination, R2 statistics to indicate level of variability accounted for by each prediction algorithm, the Hosmer-Lemeshow statistic for calibration, and the sensitivity and specificity of each algorithm. Results: The Stroke RiskometerTM performed well against the FSRS five-year AUROC for both males (FSRS=75·0% (95% CI 72·3%-77·6%), Stroke RiskometerTM=74·0(95% CI 71·3%-76·7%) and females [FSRS=70·3% (95% CI 67·9%-72·8%, Stroke RiskometerTM=71·5% (95% CI 69·0%-73·9%)], and better than QStroke [males - 59·7% (95% CI 57·3%-62·0%) and comparable to females=71·1% (95% CI 69·0%-73·1%)]. Discriminative ability of all algorithms was low (C-statistic ranging from 0·51-0·56, D-statistic ranging from 0·01-0·12). Hosmer-Lemeshow illustrated that all of the predicted risk scores were not well calibrated with the observed event data (P<0·006). Conclusions: The Stroke RiskometerTM is comparable in performance for stroke prediction with FSRS and QStroke. All three algorithms performed equally poorly in predicting stroke events. The Stroke RiskometerTM will be continually developed and validated to address the need to improve the current stroke risk scoring systems to more accurately predict stroke, particularly by identifying robust ethnic/race ethnicity group and country specific risk factors. International Journal of Stroke

/pdf/the-stroke-riskometer-tm-app-validation-of-a-data-collection-49vuv47xun.pdf

The Stroke Riskometer(TM) App: validation of a data collection tool and stroke risk predictor

The Distributed Denial of Service attack is one of the most common attacks and it is hard to mitigate, however, it has become more difficult while dealing with the Low-rate DoS (LDoS) attacks. The LDoS exploits the vulnerability of TCP congestion-control mechanism by sending malicious traffic at the low constant rate and influence the victim machine. Recently, machine learning approaches are applied to detect the complex DDoS attacks and improve the efficiency and robustness of the intrusion detection system. In this research, the algorithm is designed to balance the detection rate and its efficiency. The detection algorithm combines the Power Spectral Density (PSD) entropy function and Support Vector Machine to detect LDoS traffic from normal traffic. In our solution, the detection rate and efficiency are adjustable based on the parameter in the decision algorithm. To have high efficiency, the detection method will always detect the attacks by calculating PSD-entropy first and compare it with the two adaptive thresholds. The thresholds can efficiently filter nearly 19% of the samples with a high detection rate. To minimize the computational cost and look only for the patterns that are most relevant for detection, Support Vector Machine based machine learning model is applied to learn the traffic pattern and select appropriate features for detection algorithm. The experimental results show that the proposed approach can detect 99.19% of the LDoS attacks and has an O (n log n) time complexity in the best case.

Low-Rate DoS Attack Detection Using PSD Based Entropy and Machine Learning

Smartphones can play a significant role in maintaining decent Quality of Life for elderly people Key factor to Smartphones usage success among elderly people depends on the accessibility of phone interface In this paper, we present preliminary evaluation results of our PhonAge, an accessible and adaptable interface for Smartphones that is customized to the elderly profile The results of the evaluation show adequacy of the interface to elderly needs The evaluation feedbacks also helped in improving PhonAge interface design

/pdf/evaluation-of-phonage-an-adapted-smartphone-interface-for-1ogiqhhvw2.pdf

Evaluation of PhonAge: An Adapted Smartphone Interface for Elderly People

Due to the changing behavior of ransomware, traditional classification and detection techniques do not accurately detect new variants of ransomware Attackers use polymorphic and metamorphic techniques to avoid detection of signature-based systems We use machine learning classification to identify modified variants of ransomware based on their behavior To conduct our study, we used behavioral reports of 150 ransomware samples from 10 different ransomware families Our data-set includes some of the newest ransomware samples available, providing an evaluation of the classification accuracy of machine learning algorithms on the current evolving status of ransomware An iterative approach is used to identify optimum behavioral attributes used to achieve best classification accuracy Two main parts of this study are identification of the behavioral attributes which can be used for optimal classification accuracy and classification of ransomware using machine learning algorithms We have evaluated classification accuracy of three machine learning classification algorithms

Behavioral-Based Classification and Identification of Ransomware Variants Using Machine Learning

SmartPhones can play a significant role in maintaining decent a Quality of Life for elderly people. There are numerous solutions available on SmartPhones that can assist the elderly in their activities of daily living, however these solutions are sometimes not welcomed in elderly community due to usability and accessibility factors. In this paper, we present PhonAge, an accessible & adaptable solution for SmartPhones that can host diverse useful services to elderly people. The first stage user evaluation results shows the usability of our solution.

PhonAge: Adapted SmartPhone for Aging Population

Performance evaluation process identifies direction for future research and development. Tremendous efforts have been invested in the related research; however, no standard or commonly accepted methodology exists for evaluating and driving future research. In this paper, we review challenges, requirements, and approaches for evaluating pervasive computing systems. To position evaluation efforts presented in literature, we assembled a design and evaluation life cycle. This review is conducted to have a clear understanding of available solutions and their limitations in order to help in establishing strategy for designing comprehensive evaluation framework for pervasive computing systems.

Yasir Malik

Papers

Low-Rate DoS Attack Detection Using PSD Based Entropy and Machine Learning

Evaluation of PhonAge: An Adapted Smartphone Interface for Elderly People

Behavioral-Based Classification and Identification of Ransomware Variants Using Machine Learning

PhonAge: Adapted SmartPhone for Aging Population

Review of Challenges, Requirements, and Approaches of Pervasive Computing System Evaluation