Recent advances in deep learning (DL) have led many contemporary automatic modulation classification (AMC) techniques to use deep networks in classifying the modulation type of incoming signals at the receiver. However, current DL-based methods face scalability challenges, particularly when encountering unseen modulations or input signals from environments not present during model training, making them less suitable for real-world applications like software-defined radio devices. In this paper, we introduce a scalable AMC scheme that provides flexibility for new modulations and adaptability to input signals with diverse configurations. We propose the Meta-Transformer, a meta-learning framework based on few-shot learning (FSL) to acquire general knowledge and a learning method for AMC tasks. This approach empowers the model to identify new unseen modulations using only a very small number of samples, eliminating the need for complete model retraining. Furthermore, we enhance the scalability of the classifier by leveraging main-sub transformer-based encoders, enabling efficient processing of input signals with diverse setups. Extensive evaluations demonstrate that the proposed AMC method outperforms existing techniques across all signal-to-noise ratios (SNRs) on RadioML2018.01A. The source code and pre-trained models are released at https://github.com/cheeseBG/meta-transformer-amc .

As the quantity and complexity of network threats grow, Intrusion Detection Systems (IDSs) have become critical for securing networks. Achieving computer network intrusion detection with these IDSs requires high-level information technology and security expertise because malicious traffic has to be rigorously analyzed and the appropriate IDS rules written to effectively detect vulnerabilities that may potentially be exploited. However, incorrect IDS rules may produce numerous false positives, thereby degrading the performance of the IDS, and even worse, paralyzing the network. In this paper, we present a novel approach that exploits the Latent Dirichle Allocation (LDA) algorithm to generate IDS rules. Our proposed method, called LDA-based Automatic Rule Generation (LARGen), automatically performs an analysis of the malicious traffic and extracts the appropriate attack signatures that will be used for IDS rules. LARGen first extracts multiple signature strings embedded in network flows. Then, the flows are classified based on the extracted signature strings, and key content strings for malicious traffic are identified through the LDA inferential topic model. Those key content strings are the core of an IDS rule that can detect malicious traffic. We study the effectiveness of LDA in the context of network attack signature generation via extensive experiments with real network trace data, consisting of both benign and malicious traffic. Experimental results confirm that threat rules generated from LARGen accurately detect every cyber attack with high accuracy.

Multi-Target Multi-Camera Tracking (MTMCT), which aims to track multiple targets within a multi-camera network, has recently attracted considerable attention due to its wide range of applications. The main challenge of MTMCT is to match local tracklets (i.e., sub-trajectories) obtained by different cameras and to combine them into global trajectories across the multi-camera network. This paper addresses the cross-camera tracklet matching problem in scenarios with partially overlapping fields of view (FOVs), such as indoor multi-camera environments. We present a new lightweight matching method for the MTMC task that employs similarity analysis for location features. The proposed approach comprises two steps: (i) extracting the motion information of targets based on a ground projection method and (ii) matching the tracklets using similarity analysis based on the Dynamic Time Warping (DTW) algorithm. We use a Kanade–Lucas–Tomasi (KLT) algorithm-based frame-skipping method to reduce the computational overhead in object detection and to produce a smooth estimate of the target’s local tracklets. To improve matching accuracy, we also investigate three different location features to determine the most appropriate feature for similarity analysis. The effectiveness of the proposed method has been evaluated through real experiments, demonstrating its ability to accurately match local tracklets.

Gait-based gender classification is a challenging task since people may walk in different directions with varying speed, gait style, and occluded joints. The majority of research studies in the literature focused on gender-specific joints, while there is less attention on the comparison of all of a body’s joints. To consider all of the joints, it is essential to determine a person’s gender based on their gait using a Kinect sensor. This paper proposes a logistic-regression-based machine learning model using whole body joints for gender classification. The proposed method consists of different phases including gait feature extraction based on three dimensional (3D) positions, feature selection, and classification of human gender. The Kinect sensor is used to extract 3D features of different joints. Different statistical tools such as Cronbach’s alpha, correlation, t-test, and ANOVA techniques are exploited to select significant joints. The Coronbach’s alpha technique yields an average result of 99.74%, which indicates the reliability of joints. Similarly, the correlation results indicate that there is significant difference between male and female joints during gait. t-test and ANOVA approaches demonstrate that all twenty joints are statistically significant for gender classification, because the p-value for each joint is zero and less than 1%. Finally, classification is performed based on the selected features using binary logistic regression model. A total of hundred (100) volunteers participated in the experiments in real scenario. The suggested method successfully classifies gender based on 3D features recorded in real-time using machine learning classifier with an accuracy of 98.0% using all body joints. The proposed method outperformed the existing systems which mostly rely on digital images.

As Bring Your Own Device (BYOD) policy has become widely accepted in the enterprise, anyone with a mobile device that supports Wi-Fi tethering can provide an active wireless Internet connection to other devices without restriction from network administrators. Despite the potential benefits of Wi-Fi tethering, it raises new security issues. The open source nature of mobile operating systems (e.g., Google Android or OpenWrt) can be easily manipulated by selfish users to provide an unfair advantage throughput performance to their tethered devices. The unauthorized tethering can interfere with nearby well-planned access points (APs) within Wi-Fi networks, which results in serious performance problems. In this paper, we first conduct an extensive evaluation study and demonstrate that the abuse of Wi-Fi tethering that adjusts the clear channel access parameters has strong adverse effects in Wi-Fi networks, while providing the manipulated device a high throughput gain. Subsequently, an online detection scheme diagnoses the network condition and detects selfish tethering devices by passively exploiting the packet loss information of on-going transmissions. Our evaluation results show that the proposed method accurately distinguishes the manipulated tethering behavior from other types of misbehavior, including the hidden node problem.

Intelligent video analytics systems have come to play an essential role in many fields, including public safety, transportation safety, and many other industrial areas, such as automated tools for data extraction, and analyzing huge datasets, such as multiple live video streams transmitted from a large number of cameras. A key characteristic of such systems is that it is critical to perform real-time analytics so as to provide timely actionable alerts on various tasks, activities, and conditions. Due to the computation-intensive and bandwidth-intensive nature of these operations, however, video analytics servers may not fulfill the requirements when serving a large number of cameras simultaneously. To handle these challenges, we present an edge computing-based system that minimizes the transfer of video data from the surveillance camera feeds on a cloud video analytics server. Based on a novel approach of utilizing the information from the encoded bitstream, the edge can achieve low processing complexity of object tracking in surveillance videos and filter non-motion frames from the list of data that will be forwarded to the cloud server. To demonstrate the effectiveness of our approach, we implemented a video surveillance prototype consisting of edge devices with low computational capacity and a GPU-enabled server. The evaluation results show that our method can efficiently catch the characteristics of the frame and is compatible with the edge-to-cloud platform in terms of accuracy and delay sensitivity. The average processing time of this method is approximately 39 ms/frame with high definition resolution video, which outperforms most of the state-of-the-art methods. In addition to the scenario implementation of the proposed system, the method helps the cloud server reduce 49% of the load of the GPU, 49% that of the CPU, and 55% of the network traffic while maintaining the accuracy of video analytics event detection.