
Software and Communications

Ransomware Clustering and Classification using Similarity Matrix
Ransomwares are amongst the most dangerous malwares that face and affect any business by restricting data access or leaking sensitive information over the internet. Ransomwares binary analysis can provide a way to define the relationships between distinct features employed by ransomware families. Malware classification and clustering systems offer an effective malware indexing with search functionalities, similarity checking, samples classification and clustering. Most studies focus on the static and dynamic features extraction, machine and deep learning or visualization techniques used to

Rice Plant Disease Detection and Diagnosis Using Deep Convolutional Neural Networks and Multispectral Imaging
Rice is considered a strategic crop in Egypt as it is regularly consumed in the Egyptian people’s diet. Even though Egypt is the highest rice producer in Africa with a share of 6 million tons per year [5], it still imports rice to satisfy its local needs due to production loss, especially due to rice disease. Rice blast disease is responsible for 30% loss in rice production worldwide [9]. Therefore, it is crucial to target limiting yield damage by detecting rice crops diseases in its early stages. This paper introduces a public multispectral and RGB images dataset and a deep learning pipeline
Autonomous Traffic-Aware and QoS-Constrained Capacity Cell Shutdown for Green Mobile Networks
Energy efficiency of Radio Access Networks (RANs) is increasingly becoming a global strategic priority for Mobile Network Operators (MNOs) and governments to attain sustainable and uninterruptible network services. In this work, we propose an autonomous Machine Learning (ML)-based framework to maximize RAN energy efficiency via underutilized radio resource shutdown while maintaining an adequate network capacity with a preset Quality-Of-Service (QoS) level. This is achieved by dynamically switching radio resources on and off according to service demand. Training on a live network dataset and

A distributed real-time recommender system for big data streams
Recommender Systems (RS) play a crucial role in our lives. As users become continuously connected to the internet, they are less tolerant of obsolete recommendations made by an RS. Online RS has to address three requirements: continuous training and recommendation, handling concept drifts, and the ability to scale. Streaming RS proposed in the literature address the first two requirements only. That is because they run the training process on a single machine. To tackle the third challenge, we propose a Splitting and Replication mechanism for distributed streaming RS. Our mechanism is inspired

Evaluation of Software Static Analyzers
With the massive increase of software applications and websites, testing has become a very important concern in the software development process. This is due to the spread of a large number of security flaws. Dynamic testing requires code execution to examine the functional and non-functional behavior of software systems. It requires more time and cost, and it finds fewer bugs. On the other hand, static testing is done before code deployment and without code execution. Additionally, it provides a comprehensive diagnostics of code and focuses more on defects prevention. This provides greater

A Framework for Democratizing Open-Source Decision-Making using Decentralized Autonomous Organization
The open Source Software (OSS) became the backbone of the most heavily used technologies, including operating systems, cloud computing, AI, Blockchain, Bigdata Systems, IoT, and many more. Although the OSS individual contributors are the primary power for developing the OSS projects, they do not contribute to the OSS project's decisionmaking as much as their contributions in the OSS Projects development. This paper proposes a framework to democratize the OSS Project's decision-making using a blockchain-related technology called Decentralized Autonomous Organization (DAO). Using DAO

Anomaly-Based Intrusion Detection for Blackhole Attack Mitigation
In the contemporary environment, mobile ad hoc networks (MANETs) are becoming necessary. They are absolutely vital in a variety of situations where setting up a network quickly is required; however, this is infeasible due to low resources. Ad hoc networks have many applications: education, on the front lines of battle, rescue missions, etc. These networks are distinguished by high mobility and constrained compute, storage, and energy capabilities. As a result of a lack of infrastructure, they do not use communication tools related to infrastructure. Instead, these networks rely on one another
Study of LiDAR Segmentation and Model’s Uncertainty using Transformer for Different Pre-trainings∗
For the task of semantic segmentation of 2D or 3D inputs, Transformer architecture suffers limitation in the ability of localization because of lacking low-level details. Also for the Transformer to function well, it has to be pre-trained first. Still pre-training the Transformer is an open area of research. In this work, Transformer is integrated into the U-Net architecture as (Chen et al., 2021). The new architecture is trained to conduct semantic segmentation of 2D spherical images generated from projecting the 3D LiDAR point cloud. Such integration allows capturing the the local

Detecting Mimikatz in Lateral Movements Using Windows API Call Sequence Analysis
Advanced Persistent Threat (APT) is classified as a high threat stealthy attack on modern networks. It uses sophisticated techniques, which makes it very challenging to be detected. It can remain undetectable for an extended period by gaining unauthorized access and lateral movements in the target network. Depending on the APT group tools, responding to the initiated attack can be challenging and composite. Mimikatz is a credential theft tool used in many APT attacks to achieve their objectives. It calls Windows APIs in a particular order during the execution time. This makes the APT group
A novel artificial intelligent-based approach for real time prediction of telecom customer’s coming interaction
Predicting customer’s behavior is one of the great challenges and obstacles for business nowadays. Companies take advantage of identifying these future behaviors to optimize business outcomes and create more powerful marketing strategies. This work presents a novel real-time framework that can predict the customer’s next interaction and the time of that interaction (when that interaction takes place). Furthermore, an extensive data exploratory analysis is performed to gain more insights from the data to identify the important features. Transactional data and static profile data are integrated