Chaonan Xin^*, Keqing Xu

Journal of Cyber Security, Vol.7, pp. 483-503, 2025, DOI:10.32604/jcs.2025.071627 - 28 November 2025

Abstract Intrusion Detection Systems (IDS) have achieved high accuracy on benchmark datasets, yet models often fail to generalize across different network environments. In this paper, we propose Transformer-IDS, a transformer-based network intrusion detection model designed for cross-dataset generalization. The model incorporates a classification token, multi-head self-attention, and embedding layers to learn versatile features, and it introduces a calibration module and an AUC-oriented optimization objective to improve reliability and ranking performance. We evaluate Transformer-IDS on three prominent datasets (NSL-KDD, UNSW-NB15, CIC-IDS2017) in both within-dataset and cross-dataset scenarios. Results demonstrate that while conventional deep IDS models (e.g., CNN-LSTM More >

Jinghua Yang¹, Bin Gong^1,2,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.3, pp. 1-2, 2025, DOI: 10.32604/icces.2025.011889

Abstract Geological stratification interpretation divides geological strata based on acquired well-logging data, providing comparative analysis results for strata and structures. This process serves as a fundamental framework for subsequent drilling and development design plans, making it a crucial step in oil exploration and development process. Traditional geological stratification interpretation methods are based primarily on geological, logging, and experimental data, with manual determination of strata boundaries to obtain interpretation results. However, manual interpretation is characterized by strong subjectivity and reliance on experience, which may compromise the quality and consistency of the results. To eliminate the dependency on… More >

Abubakar Elsafi^*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.2, pp. 1749-1766, 2025, DOI:10.32604/cmes.2025.066449 - 31 August 2025

Abstract Domain randomization is a widely adopted technique in deep reinforcement learning (DRL) to improve agent generalization by exposing policies to diverse environmental conditions. This paper investigates the impact of different reset strategies, normal, non-randomized, and randomized, on agent performance using the Deep Deterministic Policy Gradient (DDPG) and Twin Delayed DDPG (TD3) algorithms within the CarRacing-v2 environment. Two experimental setups were conducted: an extended training regime with DDPG for 1000 steps per episode across 1000 episodes, and a fast execution setup comparing DDPG and TD3 for 30 episodes with 50 steps per episode under constrained computational… More >

Smita Khairnar^1,2, Shilpa Gite^1,3,*, Biswajeet Pradhan^4,*, Sudeep D. Thepade^2,5, Abdullah Alamri⁶

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 3677-3707, 2025, DOI:10.32604/cmes.2025.058855 - 30 June 2025

Abstract Face liveness detection is essential for securing biometric authentication systems against spoofing attacks, including printed photos, replay videos, and 3D masks. This study systematically evaluates pre-trained CNN models— DenseNet201, VGG16, InceptionV3, ResNet50, VGG19, MobileNetV2, Xception, and InceptionResNetV2—leveraging transfer learning and fine-tuning to enhance liveness detection performance. The models were trained and tested on NUAA and Replay-Attack datasets, with cross-dataset generalization validated on SiW-MV2 to assess real-world adaptability. Performance was evaluated using accuracy, precision, recall, FAR, FRR, HTER, and specialized spoof detection metrics (APCER, NPCER, ACER). Fine-tuning significantly improved detection accuracy, with DenseNet201 achieving the highest… More > Graphic Abstract

Priyadharsini Selvaraj^1,*, Senthil Kumar Jagatheesaperumal², Karthiga Marimuthu¹, Oviya Saravanan¹, Bader Fahad Alkhamees³, Mohammad Mehedi Hassan^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.2, pp. 1575-1594, 2025, DOI:10.32604/cmes.2025.064138 - 30 May 2025

Abstract With expeditious advancements in AI-driven facial manipulation techniques, particularly deepfake technology, there is growing concern over its potential misuse. Deepfakes pose a significant threat to society, particularly by infringing on individuals’ privacy. Amid significant endeavors to fabricate systems for identifying deepfake fabrications, existing methodologies often face hurdles in adjusting to innovative forgery techniques and demonstrate increased vulnerability to image and video clarity variations, thereby hindering their broad applicability to images and videos produced by unfamiliar technologies. In this manuscript, we endorse resilient training tactics to amplify generalization capabilities. In adversarial training, models are trained using More >

Huyong Yan¹, Huidong Zhou^2,*, Jian Zheng¹, Zhaozhe Zhou¹

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4659-4677, 2025, DOI:10.32604/cmc.2025.062807 - 19 May 2025

Abstract As smart manufacturing and Industry 4.0 continue to evolve, fault diagnosis of mechanical equipment has become crucial for ensuring production safety and optimizing equipment utilization. To address the challenge of cross-domain adaptation in intelligent diagnostic models under varying operational conditions, this paper introduces the CNN-1D-KAN model, which combines a 1D Convolutional Neural Network (1D-CNN) with a Kolmogorov–Arnold Network (KAN). The novelty of this approach lies in replacing the traditional 1D-CNN’s final fully connected layer with a KANLinear layer, leveraging KAN’s advanced nonlinear processing and function approximation capabilities while maintaining the simplicity of linear transformations. Experimental… More >

Zhicheng Yin^1,2, Lang Li^1,2,*, Yu Ou^1,2

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1001-1022, 2025, DOI:10.32604/cmc.2025.060925 - 26 March 2025

Abstract The adoption of deep learning-based side-channel analysis (DL-SCA) is crucial for leak detection in secure products. Many previous studies have applied this method to break targets protected with countermeasures. Despite the increasing number of studies, the problem of model overfitting. Recent research mainly focuses on exploring hyperparameters and network architectures, while offering limited insights into the effects of external factors on side-channel attacks, such as the number and type of models. This paper proposes a Side-channel Analysis method based on a Stacking ensemble, called Stacking-SCA. In our method, multiple models are deeply integrated. Through the… More >

Yonghang Yan¹, Xin Xie¹, Hengyi Ren², Ying Cao^1,*, Hongwei Chang³

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5035-5055, 2025, DOI:10.32604/cmc.2025.058276 - 06 March 2025

Abstract Fingerprint features, as unique and stable biometric identifiers, are crucial for identity verification. However, traditional centralized methods of processing these sensitive data linked to personal identity pose significant privacy risks, potentially leading to user data leakage. Federated Learning allows multiple clients to collaboratively train and optimize models without sharing raw data, effectively addressing privacy and security concerns. However, variations in fingerprint data due to factors such as region, ethnicity, sensor quality, and environmental conditions result in significant heterogeneity across clients. This heterogeneity adversely impacts the generalization ability of the global model, limiting its performance across… More >

Muhammad Ahmad^1,*, Manuel Mazzara², Salvatore Distefano³, Adil Mehmood Khan⁴, Hamad Ahmed Altuwaijri⁵

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 503-532, 2024, DOI:10.32604/cmc.2024.056318 - 15 October 2024

Abstract Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models e.g., Attention Graph and Vision Transformer. When training, validation, and test sets overlap or share data, it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new examples. This paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification (HSIC). By separating training, validation, and test data without overlap, the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was… More >

Lassaad K. Smirani¹, Leila Jamel^2,*, Latifah Almuqren²

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.2, pp. 1315-1337, 2024, DOI:10.32604/cmes.2024.047551 - 20 May 2024

Abstract This study presents a layered generalization ensemble model for next generation radio mobiles, focusing on supervised channel estimation approaches. Channel estimation typically involves the insertion of pilot symbols with a well-balanced rhythm and suitable layout. The model, called Stacked Generalization for Channel Estimation (SGCE), aims to enhance channel estimation performance by eliminating pilot insertion and improving throughput. The SGCE model incorporates six machine learning methods: random forest (RF), gradient boosting machine (GB), light gradient boosting machine (LGBM), support vector regression (SVR), extremely randomized tree (ERT), and extreme gradient boosting (XGB). By generating meta-data from five… More >