Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


James Msughter Adeke has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism

    by Nannan Wu, Xianyi Chen, James Msughter Adeke, Junjie Zhao

    Recently, deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information hiding. However, these approaches have some limitations. For example, a cover image lacks self-adaptability, information leakage, or weak concealment. To address these issues, this study proposes a universal and adaptable image-hiding method. First, a domain attention mechanism is designed by combining the Atrous convolution, which makes better use of the relationship between the secret image domain and the cover image domain. Second, to improve perceived human similarity, perceptual loss is incorporated into the training process. The experimental results are promising, with the proposed method achieving an average pixel discrepancy (APD) of 1.83 and a peak signal-to-noise ratio (PSNR) value of 40.72 dB between the cover and stego images, indicative of its high-quality output. Furthermore, the structural similarity index measure (SSIM) reaches 0.985 while the learned perceptual image patch similarity (LPIPS) remarkably registers at 0.0001. Moreover, self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces, making it suitable for diverse computer vision tasks.


  • Open Access

    Boosting Adversarial Training with Learnable Distribution

    by Kai Chen, Jinwei Wang, James Msughter Adeke, Guangjie Liu, Yuewei Dai

    In recent years, various adversarial defense methods have been proposed to improve the robustness of deep neural networks. Adversarial training is one of the most potent methods to defend against adversarial attacks. However, the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training. This paper proposes a learnable distribution adversarial training method, aiming to construct the same distribution for training data utilizing the Gaussian mixture model. The distribution centroid is built to classify samples and constrain the distribution of the sample features. The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model. The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training. This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation. Finally, the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid. The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense. The effectiveness of the proposed method is demonstrated through comprehensive experiments.


  • Open Access

    Passenger Flow Prediction Method based on Hybrid Algorithm: Intelligent Transportation System

    by Ahmed Raza, Guangjie Liu, James Msughter Adeke, Jie Cheng, Danish Attique

    Forecasting passenger flow at metro transit stations is a useful method for optimizing the organization of passenger transportation and enhancing operational safety and transportation efficiency. Aiming at the problem that the traditional ARIMA model has poor performance in predicting passenger flow, a hybrid prediction method based on ARIMA-Kalman filtering is proposed. In this regard, ARIMA model training experimental samples are integrated with Kalman filter to create a prediction recursion equation, which is then utilized to estimate passenger flow. The simulation experiment results based on the inbound passenger flow data of Nanjing metro station show that compared with the single ARIMA model, the root mean square error of the prediction results of the proposed ARIMA-Kalman filter hybrid algorithm is reduced by 257.106, and the mean absolute error decreased by 145. 675, the mean absolute percentage error dropped by 5. 655%, proving that the proposed hybrid algorithm has higher prediction accuracy. The experiment results based on the passenger flow data of Nanjing metro station show that compared to a single ARIMA model, the proposed ARIMA Kalman filtering hybrid algorithm reduces the root mean square error of the prediction results by 257.106, the average absolute error by 145.675, and the average absolute percentage error by 5.655%. It has been proven that the proposed hybrid algorithm has higher prediction accuracy.


  • Open Access

    Securing Network Traffic Classification Models against Adversarial Examples Using Derived Variables

    by James Msughter Adeke, Guangjie Liu, Junjie Zhao, Nannan Wu, Hafsat Muhammad Bashir

    Machine learning (ML) models are essential to securing communication networks. However, these models are vulnerable to adversarial examples (AEs), in which malicious inputs are modified by adversaries to produce the desired output. Adversarial training is an effective defense method against such attacks but relies on access to a substantial number of AEs, a prerequisite that entails significant computational resources and the inherent limitation of poor performance on clean data. To address these problems, this study proposes a novel approach to improve the robustness of ML-based network traffic classification models by integrating derived variables (DVars) into training. Unlike adversarial training, our approach focuses on enhancing training using DVars, introducing randomness into the input data. DVars are generated from the baseline dataset and significantly improve the resilience of the model to AEs. To evaluate the effectiveness of DVars, experiments were conducted using the CSE-CIC-IDS2018 dataset and three state-of-the-art ML-based models: decision tree (DT), random forest (RF), and k-neighbors (KNN). The results show that DVars can improve the accuracy of KNN under attack from 0.45% to 0.84% for low-intensity attacks and from 0.32% to 0.66% for high-intensity attacks. Furthermore, both DT and RF achieve a significant increase in accuracy when subjected to attack of different intensity. Moreover, DVars are computationally efficient, scalable, and do not require access to AEs.


  • Open Access

    Detecting High-Resolution Adversarial Images with Few-Shot Deep Learning

    by Junjie Zhao, Junfeng Wu, James Msughter Adeke, Sen Qiao, Jinwei Wang

    Deep learning models have enabled significant performance improvements to remote sensing image processing. Usually, a large number of training samples is required for detection models. In this study, a dynamic simulation training strategy is designed to generate samples in real time during training. The few adversarial examples are not only directly involved in the training but are also used to fit the distribution model of adversarial noise, helping the real-time generated samples to be similar to adversarial examples. The noise of the training samples is randomly generated according to the distribution model, and the random variation of training inputs reduces the overfitting phenomenon. To enhance the detectability of adversarial noise, the input model is no longer a normalized image but a JPEG error image. Experiments show that with the proposed dynamic simulation training strategy, common classification models such as ResNet and DenseNet can effectively detect adversarial examples.


  • Open Access

    EITGAN: A Transformation-based Network for recovering adversarial examples

    by Junjie Zhao, Junfeng Wu, James Msughter Adeke, Guangjie Liu, Yuewei Dai

    Adversarial examples have been shown to easily mislead neural networks, and many strategies have been proposed to defend them. To address the problem that most transformation-based defense strategies will degrade the accuracy of clean images, we proposed an Enhanced Image Transformation Generative Adversarial Network (EITGAN). Positive perturbations were employed in the EITGAN to counteract adversarial effects while enhancing the classified performance of the samples. We also used the image super-resolution method to mitigate the effect of adversarial perturbations. The proposed method does not require modification or retraining of the classifier. Extensive experiments demonstrated that the enhanced samples generated by the EITGAN effectively defended against adversarial attacks without compromising human visual recognition, and their classification performance was superior to that of clean images.


  • A Game-Theoretic Approach to Computation Offloading in Software-Defined D2D-Enabled Vehicular Networks

    by Richard N.K. Mensah, Li Zhiyuan, Andrews A. Okine, James M. Adeke

    The incipient vehicular applications and the explosive growth of data generally led to the increase in demand for communication, computation, and storage resources, as well as the stringent performance requirement on latency and wireless network capacity. To address these challenges, Vehicular Edge Computing is an envisioned promising solution that extends the computation capability to the edge of the vehicular network and computation offloading service is provided in the proximity of the vehicles. Vehicular edge computing (VEC) and D2D communication have been designed to benefit from proximity gain to optimize computation offloading. Software-defined network (SDN) inside the vehicular network (SDVN) is developed in this article to rectify most problems in the vehicular network. Besides, the SDVN controller handles D2D pairing of vehicles and co-ordinates with the edge cloud for flexible allocation of computing resources among vehicles and mobile users. In this article, we combine D2D communication and VEC to further enhance the computation capacity of the vehicular network. Our goal is to optimize the number of devices the vehicular network can support under communication and computational limitation. We formulate the task offloading and associated resource allocation problem as a game with mixed strategies. The players involved in the game are the SDN controller handling the computation resource allocation at the network edge and a vehicle deciding on task offloading. The existence and uniqueness of Nash equilibrium are theoretically proved.