Different machine learning and deep learning-based approaches have been proposed for designing defensive mechanisms against various phishing attacks. Recently, researchers showed that phishing attacks can be performed by employing a deep neural network-based phishing URL generating system called DeepPhish. To prevent this kind of attack, we design an ensemble machine learning-based detection system called PhishHaven to identify AI-generated as well as human-crafted phishing URLs. To the best of our knowledge, this is the first study to consider detecting phishing attacks by both AI and human attackers. PhishHaven employs lexical analysis for feature extraction. To further enhance lexical analysis, we introduce URL HTML Encoding to classify URL on-the-fly and proactively compare with some of the existing methods. We also introduce a URL Hit approach to deal with tiny URLs, which is an open problem yet to be solved. Moreover, the final classification of URLs is made on an unbiased voting mechanism in PhishHaven, which aims to avoid misclassification when the number of votes is equal. To speed up the ensemble-based machine learning models, PhishHaven employs a multi-threading approach to execute the classification in parallel, leading to real-time detection. Theoretical analysis of our solution shows that (1) it can always detect tiny URLs, and (2) it can detect future AI-generated Phishing URLs based on our selected lexical features with 100% accuracy. Through experiments, we analyze our solution with a benchmark dataset of 100,000 phishing and normal URLs. The results show that PhishHaven can achieve 98.00% accuracy, outperforming the existing lexical-based human-crafted phishing URLs detection systems.

Human Activity Recognition (HAR) is becoming an essential part of human life care. Existing HAR methods are usually developed using a two-level approach, wherein a first-level Machine Learning (ML) classifier is employed to distinguish the static and dynamic activities, followed by a second-level classifier to identify the specific activity. These approaches are not suitable for wearable devices, due to the high computational and memory consumption. Our rigorous analysis of various HAR datasets opens up a new possibility that static or dynamic activities can be discriminated against through a simple statistical technique. Therefore, we propose to utilize a statistical feature extraction technique to replace the first-level ML classifier, thus achieving more lightweight computation. Next, we employ Random Forest (RF) and Convolutional Neural Networks (CNN) to classify the specific activities, achieving higher accuracy compared to the state-of-the-art results. We further reduce the computation and memory consumption of the above combined approach by applying pruning and quantizing techniques to CNN (PQ-CNN). Experimental results show the proposed lightweight HAR method achieved an F1 score of 0.9417 and 0.9438 for unbalanced and balanced datasets, respectively. On top of lightweight and accuracy, the proposed HAR method is practical for wearable devices by using a single accelerometer.

In this paper, we present the enhancement of a lightweight key-policy attribute-based encryption (KP-ABE) scheme designed for the Internet of Things (IoT). The KP-ABE scheme was claimed to achieve ciphertext indistinguishability under chosen-plaintext attack in the selective-set model but we show that the KP-ABE scheme is insecure even in the weaker security notion, namely, one-way encryption under the same attack and model. In particular, we show that an attacker can decrypt a ciphertext which does not satisfy the policy imposed on his decryption key. Subsequently, we propose an efficient fix to the KP-ABE scheme as well as extending it to be a hierarchical KP-ABE (H-KP-ABE) scheme that can support role delegation in IoT applications. An example of applying our H-KP-ABE on an IoT-connected healthcare system is given to highlight the benefit of the delegation feature. Lastly, using the NIST curves secp192k1 and secp256k1, we benchmark the fixed (hierarchical) KP-ABE scheme on an Android phone and the result shows that the scheme is still the fastest in the literature.

This paper presents a multi-objective coverage flight path planning algorithm that finds minimum length, collision-free, and flyable paths for unmanned aerial vehicles (UAV) in three-dimensional (3D) urban environments inhabiting multiple obstacles for covering spatially distributed regions. In many practical applications, UAVs are often required to fully cover multiple spatially distributed regions located in the 3D urban environments while avoiding obstacles. This problem is relatively complex since it requires the optimization of both inter (e.g., traveling from one region/city to another) and intra-regional (e.g., within a region/city) paths. To solve this complex problem, we find the traversal order of each area of interest (AOI) in the form of a coarse tour (i.e., graph) with the help of an ant colony optimization (ACO) algorithm by formulating it as a traveling salesman problem (TSP) from the center of each AOI, which is subsequently optimized. The intra-regional path finding problem is solved with the integration of fitting sensors’ footprints sweeps (SFS) and sparse waypoint graphs (SWG) in the AOI. To find a path that covers all accessible points of an AOI, we fit fewer, longest, and smooth SFSs in such a way that most parts of an AOI can be covered with fewer sweeps. Furthermore, the low-cost traversal order of each SFS is computed, and SWG is constructed by connecting the SFSs while respecting the global and local constraints. It finds a global solution (i.e., inter + intra-regional path) without sacrificing the guarantees on computing time, number of turning maneuvers, perfect coverage, path overlapping, and path length. The results obtained from various representative scenarios show that proposed algorithm is able to compute low-cost coverage paths for UAV navigation in urban environments.