James Msughter Adeke
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
Research Subjects
James Msughter Adeke has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Guangjie Liu
Nanjing University of Information Science and Technology
4 shared publications - Hafsat Muhammad Bashir2 shared publications
Junjie Zhao
School of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, 210044, China
2 shared publications- Junjie Zhao
School of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
2 shared publications Yuewei Dai
School of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, 210044, China
2 shared publications- Yunquan Dong
School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China
2 shared publications
Latest Publications
- 4 June 2026
- Published by Elsevier in Physical Communication
- Vol. 78
A distortion-aware power optimization framework for secure SIMO transmission over Rayleigh fading channels
- 4 June 2026
- Published by Elsevier in Physical Communication
- Vol. 78
A distortion-aware power optimization framework for secure SIMO transmission over Rayleigh fading channels
- 9 April 2025
- Published by Elsevier in Physical Communication
- Vol. 71
Minimizing distortion and enhancing security in Rayleigh fading channels
- 9 April 2025
- Published by Elsevier in Physical Communication
- Vol. 71
Minimizing distortion and enhancing security in Rayleigh fading channels
- 15 January 2025
- Published by Elsevier in Computers & Security
- Vol. 151
Investigating the impact of feature selection on adversarial transferability in intrusion detection system
- 15 January 2025
- Published by Elsevier in Computers & Security
- Vol. 151
Investigating the impact of feature selection on adversarial transferability in intrusion detection system
- Open Access
- 1 January 2024
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 78 (3) , 3001-3019
A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism
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.
- 1 January 2024
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 78 (3) , 3001-3019
Open AccessA Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism
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
- 1 January 2024
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 78 (3) , 3247-3265
Boosting Adversarial Training with Learnable Distribution
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.
- 1 January 2024
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 78 (3) , 3247-3265
Open AccessBoosting Adversarial Training with Learnable Distribution
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
- 1 January 2024
- Published by AMO Publisher in European Journal of Applied Science, Engineering and Technology
- Vol. 2 (1) , 12-20
Passenger Flow Prediction Method based on Hybrid Algorithm: Intelligent Transportation System
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.
- 1 January 2024
- Published by AMO Publisher in European Journal of Applied Science, Engineering and Technology
- Vol. 2 (1) , 12-20
Open AccessPassenger Flow Prediction Method based on Hybrid Algorithm: Intelligent Transportation System
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
- 16 December 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (12) , 405
Securing Network Traffic Classification Models against Adversarial Examples Using Derived Variables
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.
- 16 December 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (12) , 405
Open AccessSecuring Network Traffic Classification Models against Adversarial Examples Using Derived Variables
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
- 30 April 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (9) , 2379
Detecting High-Resolution Adversarial Images with Few-Shot Deep Learning
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.
- 30 April 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (9) , 2379
Open AccessDetecting High-Resolution Adversarial Images with Few-Shot Deep Learning
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
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 31 (11) , 6634-6656
EITGAN: A Transformation-based Network for recovering adversarial examples
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.
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 31 (11) , 6634-6656
Open AccessEITGAN: A Transformation-based Network for recovering adversarial examples
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.
- 7 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 34-38
A Game-Theoretic Approach to Computation Offloading in Software-Defined D2D-Enabled Vehicular Networks
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.
- 7 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 34-38
A Game-Theoretic Approach to Computation Offloading in Software-Defined D2D-Enabled Vehicular Networks
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.