In July 2021, the IT management software company Kaseya was the victim of a ransomware cyberattack. The perpetrator of this attack was ransomware evil (REvil), an allegedly Russian‐based ransomware threat group. This paper addresses the general events of the incident and the actions executed by the constituents involved. The attack was conducted through specially crafted hypertext transfer protocol (HTTP) requests to circumvent authentication and allow hackers to upload malicious payloads through Kaseya’s virtual system administrator (VSA). The attack led to the emergency shutdown of many VSA servers and a federal investigation. REvil has had a tremendous impact performing ransomware operations, including worsening international relations between Russia and world leaders and costing considerable infrastructure damage and millions of dollars in ransom payments. We present an overview of Kaseya’s defense strategy involving customer interaction, a PowerShell script to detect compromised clients, and a cure‐all decryption key that unlocks all locked files.

This article analyzes SplitFed Learning against model poisoning vulnerability and develops methods to protect such a system against these attacks. SplitFed learning is a distributed learning paradigm where a neural network model is split between clients and the server, contrasting with traditional Federated Learning. SplitFed learning enables enhanced security and data privacy, and clients do not need to perform heavy computation in model training, as they only need to train a part of the model. This approach ensures that the model can make precise predictions while maintaining the confidentiality of sensitive information. In addition to implementing a SplitFed model, the paper proposes a distance-based method that can poison SplitFed learning-based systems. Subsequently, this paper develops a novel prevention strategy based on robust statistical properties of the sample. To test the proposed methodology, we used the image cell dataset of the malaria parasite as a test case. By addressing the impacts of adversarial attacks, this paper contributes to the advancement of deep learning techniques.

Healthcare is one of the foremost applications of machine learning (ML). Traditionally, ML models are trained by central servers, which aggregate data from various distributed devices to forecast the results for newly generated data. This is a major concern as models can access sensitive user information, which raises privacy concerns. A federated learning (FL) approach can help address this issue: A global model sends its copy to all clients who train these copies, and the clients send the updates (weights) back to it. Over time, the global model improves and becomes more accurate. Data privacy is protected during training, as it is conducted locally on the clients’ devices.However, the global model is susceptible to data poisoning. We develop a privacy-preserving FL technique for a skin cancer dataset and show that the model is prone to data poisoning attacks. Ten clients train the model, but one of them intentionally introduces flipped labels as an attack. This reduces the accuracy of the global model. As the percentage of label flipping increases, there is a noticeable decrease in accuracy. We use a stochastic gradient descent optimization algorithm to find the most optimal accuracy for the model. Although FL can protect user privacy for healthcare diagnostics, it is also vulnerable to data poisoning, which must be addressed.

In this paper, we explore the problem of finding the initial positions to deploy UAVs to provide service to ground personnel. In this work, we propose a greedy algorithm that finds a feasible solution that guarantees 100% coverage on any given map. We defined subareas of the map which do not need coverage as excluding zones. We considered both excluding zones and the connectivity constraints in the algorithm. By avoiding these zones and keeping all nodes connected to the network we can reduce the total number of UAVs needed to provide coverage without losing the communication capability. We show that the complexity of the algorithm is linear with respect to the input parameters. Simulation results show the behavior of our approach with different maps. We observe a convergence on the number of nodes needed when varying the input map.