Cyber-security of modern power systems has captured a significant interest. The vulnerabilities in the cyber infrastructure of the power systems provide an avenue for adversaries to launch cyber attacks. An example of such cyber attacks is False Data Injection Attacks (FDIA). The main contribution of this paper is to analyze the impact of FDIA on the cost of power generation and the physical component of the power systems. Furthermore, We introduce a new FDIA strategy that intends to maximize the cost of power generation. The viability of the attack is shown using simulations on the standard IEEE bus systems using the MATPOWER MATLAB package. We used the genetic algorithm (GA), simulated annealing (SA) algorithm, tabu search (TS), and particle swarm optimization (PSO) to find the suitable attack targets and execute FDIA in the power systems. The proposed FDIA increases the generation cost by up to 15.6%, 45.1%, 60.12%, and 74.02% on the 6-bus, 9-bus, 30-bus, and 118-bus systems, respectively. Finally, a rule-based FDIA detection and prevention mechanism is proposed to mitigate such attacks on power systems.

In digital forensics, file carving is used to extract files without relying on the underlying file system metadata. This process can be challenging if the file is fragmented. Therefore, it is important first to identify the type of file fragment. There exist several techniques to identify the type of file fragments without relying on metadata, for example, using headers and footers to identify the fragment type. Recently, convolutional neural network (CNN) models have been used to build classification models to achieve this task. Existing models for file fragment type classification often require significant computational resources due to their large number of parameters, leading to slower inference times and higher memory consumption. To address these challenges, we propose light-weight file fragment type classification models based on separable CNNs that maintain comparable accuracy while reducing computational demands. Our proposed light-weight file fragment type classification model leverages depthwise separable convolutions to improve the efficiency of feature extraction while reducing computational overhead. This approach leads to improved classification performance by focusing on the most relevant features within file fragments, achieving comparable accuracy to state-of-the-art models with significantly fewer parameters. The evaluation results demonstrate the model’s effectiveness, with a 79% accuracy on the FFT-75 dataset using nearly 100K parameters and 164M FLOPs —representing a 4x reduction in model size and a 6x improvement in speed over the best-performing existing classifier. Our results demonstrate that these light-weight models are effective for real-time digital forensic applications where computational efficiency is critical.

In this paper, we propose a preference-aware cooperative video streaming system for videos encoded using scalable video coding (SVC). In the proposed system, the collaborating users are interested in watching a video together on a shared screen. However, the willingness of each user to cooperate is subject to her own constraints such as user data plans. Using SVC, videos are segmented into chunks and each chunk is encoded using layers, where each layer can be fetched through any of the collaborating users. We formulate the problem of finding the optimal quality decisions and fetching policy of the SVC layers of video chunks subject to the available bandwidth, chunk deadlines, and cooperation willingness of the different users as an optimization problem. The objective is to optimize a QoE metric that maintains a trade-off between maximizing the playback rate of every chunk and ensuring fairness among all chunks to achieve the minimum skip (stall) duration without violating any of the imposed constraints. We propose an offline algorithm to solve the non-convex optimization problem when the bandwidth prediction is non-causally known. This algorithm has a run-time complexity that is polynomial in the video length and the number of collaborating users. Furthermore, we propose an online version of the algorithm for practical scenarios, where erroneous bandwidth prediction for a short window is used. Real implementation with android devices using SVC encoded video and a public dataset of bandwidth traces reveals the robustness and performance of the proposed algorithm and shows that the algorithm significantly outperforms round robin-based mechanisms in terms of avoiding skips/stalls and fetching video chunks at their highest quality possible.

Federated Learning (FL) has transformed machine learning by facilitating decentralized, privacy-focused data processing. Despite its advantages, FL remains vulnerable to data poisoning attacks, particularly Label-Flipping Attacks (LFA). In LFA, malicious clients deliberately mislabel local data, causing the global model to misclassify certain classes, thus undermining its integrity. Although centralized detection methods have been explored, there is a notable gap in addressing LFA within the decentralized Client-Edge-Cloud architecture, which is crucial for FL systems. This study introduces an innovative edge-assisted framework for early detection of LFA, crucial for real-time applications. To our knowledge, this is the first study to propose such an edge-assisted LFA detection mechanism. Through detailed conceptual and empirical analyses of LFA behavior, we identified a key characteristic: class-wise accuracy, particularly recall for specific classes, decreases due to label flipping, significantly increases the delta discrepancy with the edge model. Our method remains effective across varying numbers of malicious clients and model sizes, without requiring prior knowledge about the malicious clients. We developed two mitigation strategies: (1) the Zero Tolerance approach, which excludes entire client updates upon detecting adversarial behavior, and (2) the Zero Masking approach, which zeros out gradients for the flipped class while preserving others. This method leverages the direct influence of final layer gradients on class predictions. Extensive evaluation using three benchmark datasets shows that the proposed edge-assisted LFA detection framework outperforms traditional cloud-based methods. We demonstrate its superiority in latency, resource efficiency, and accuracy in detecting malicious clients, outperforming state-of-the-art defenses.

The Q-problem is a new lightweight and hard mathematical problem that resists quantum attacks. It depends on putting one known value and two unknown values per equation; whatever the operator, the Q-problem defines certain conditions between equations. This paper presents a new key exchange protocol based on the Q-problem. To protect secure end-to-end communication over a public transmission channel, the proposed mechanism consists of two rounds of exchanging totally random numbers, which ensure a shared secret key between two parties at the end. Security analysis proves the robustness of the proposal and experiments prove its lightness during implementation, making it a promising protocol of hybrid solutions and an assistive technique for the transition to the quantum era.