Junaid Arshad

Anum Paracha, Junaid Arshad, Mohamed Ben Farah et al.

Poisoning attacks are a primary threat to machine learning models, aiming to compromise their performance and reliability by manipulating training datasets. This paper introduces a novel attack - Outlier-Oriented Poisoning (OOP) attack, which manipulates labels of most distanced samples from the decision boundaries. The paper also investigates the adverse impact of such attacks on different machine learning algorithms within a multiclass classification scenario, analyzing their variance and correlation between different poisoning levels and performance degradation. To ascertain the severity of the OOP attack for different degrees (5% - 25%) of poisoning, we analyzed variance, accuracy, precision, recall, f1-score, and false positive rate for chosen ML models.Benchmarking our OOP attack, we have analyzed key characteristics of multiclass machine learning algorithms and their sensitivity to poisoning attacks. Our experimentation used three publicly available datasets: IRIS, MNIST, and ISIC. Our analysis shows that KNN and GNB are the most affected algorithms with a decrease in accuracy of 22.81% and 56.07% while increasing false positive rate to 17.14% and 40.45% for IRIS dataset with 15% poisoning. Further, Decision Trees and Random Forest are the most resilient algorithms with the least accuracy disruption of 12.28% and 17.52% with 15% poisoning of the IRIS dataset. We have also analyzed the correlation between number of dataset classes and the performance degradation of models. Our analysis highlighted that number of classes are inversely proportional to the performance degradation, specifically the decrease in accuracy of the models, which is normalized with increasing number of classes. Further, our analysis identified that imbalanced dataset distribution can aggravate the impact of poisoning for machine learning models

Anum Paracha, Junaid Arshad, Mohamed Ben Farah et al.

Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned with particular ML algorithms. Furthermore, most defenses are developed to secure deep neural networks or binary classifiers. However, traditional multiclass classifiers need attention to be secure from data poisoning attacks, as these models are significant in developing multi-modal applications. Therefore, this paper proposes SecureLearn, a two-layer attack-agnostic defense to defend multiclass models from poisoning attacks. It comprises two components of data sanitization and a new feature-oriented adversarial training. To ascertain the effectiveness of SecureLearn, we proposed a 3D evaluation matrix with three orthogonal dimensions: data poisoning attack, data sanitization and adversarial training. Benchmarking SecureLearn in a 3D matrix, a detailed analysis is conducted at different poisoning levels (10%-20%), particularly analysing accuracy, recall, F1-score, detection and correction rates, and false discovery rate. The experimentation is conducted for four ML algorithms, namely Random Forest (RF), Decision Tree (DT), Gaussian Naive Bayes (GNB) and Multilayer Perceptron (MLP), trained with three public datasets, against three poisoning attacks and compared with two existing mitigations. Our results highlight that SecureLearn is effective against the provided attacks. SecureLearn has strengthened resilience and adversarial robustness of traditional multiclass models and neural networks, confirming its generalization beyond algorithm-specific defenses. It consistently maintained accuracy above 90%, recall and F1-score above 75%. For neural networks, SecureLearn achieved 97% recall and F1-score against all selected poisoning attacks.

Muhammad Ajmal Azad, Junaid Arshad, Ali Akmal et al.

Today's smartphones are equipped with a large number of powerful value-added sensors and features such as a low power Bluetooth sensor, powerful embedded sensors such as the digital compass, accelerometer, GPS sensors, Wi-Fi capabilities, microphone, humidity sensors, health tracking sensors, and a camera, etc. These value-added sensors have revolutionized the lives of the human being in many ways such, as tracking the health of the patients and movement of doctors, tracking employees movement in large manufacturing units, and monitoring the environment, etc. These embedded sensors could also be used for large-scale personal, group, and community sensing applications especially tracing the spread of certain diseases. Governments and regulators are turning to use these features to trace the people thought to have symptoms of certain diseases or virus e.g. COVID-19. The outbreak of COVID-19 in December 2019, has seen a surge of the mobile applications for tracing, tracking and isolating the persons showing COVID-19 symptoms to limit the spread of disease to the larger community. The use of embedded sensors could disclose private information of the users thus potentially bring threat to the privacy and security of users. In this paper, we analyzed a large set of smartphone applications that have been designed to contain the spread of the COVID-19 virus and bring the people back to normal life. Specifically, we have analyzed what type of permission these smartphone apps require, whether these permissions are necessary for the track and trace, how data from the user devices is transported to the analytic center, and analyzing the security measures these apps have deployed to ensure the privacy and security of users.

Junaid Arshad, Muhammad Ajmal Azad, Khaled Salah et al.

Internet of Things (IoT) is a disruptive technology with applications across diverse domains such as transportation and logistics systems, smart grids, smart homes, connected vehicles, and smart cities. Alongside the growth of these infrastructures, the volume and variety of attacks on these infrastructures has increased highlighting the significance of distinct protection mechanisms. Intrusion detection is one of the distinguished protection mechanisms with notable recent efforts made to establish effective intrusion detection for IoT and IoV. However, unique characteristics of such infrastructures including battery power, bandwidth and processors overheads, and the network dynamics can influence the operation of an intrusion detection system. This paper presents a comprehensive study of existing intrusion detection systems for IoT systems including emerging systems such as Internet of Vehicles (IoV). The paper analyzes existing systems in three aspects: computational overhead, energy consumption and privacy implications. Based on a rigorous analysis of the existing intrusion detection approaches, the paper also identifies open challenges for an effective and collaborative design of intrusion detection system for resource-constrained IoT system in general and its applications such as IoV. These efforts are envisaged to highlight state of the art with respect to intrusion detection for IoT and open challenges requiring specific efforts to achieve efficient intrusion detection within these systems.