Ahmet Emre Ergün, Aytuğ Onan^*

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4855-4877, 2025, DOI:10.32604/cmc.2025.063826 - 19 May 2025

Abstract Large Language Models (LLMs) have significantly advanced human-computer interaction by improving natural language understanding and generation. However, their vulnerability to adversarial prompts–carefully designed inputs that manipulate model outputs–presents substantial challenges. This paper introduces a classification-based approach to detect adversarial prompts by utilizing both prompt features and prompt response features. Eleven machine learning models were evaluated based on key metrics such as accuracy, precision, recall, and F1-score. The results show that the Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) cascade model delivers the best performance, especially when using prompt features, achieving an accuracy of over 97% in… More >

Qing Xie^*, Ruiyun Yu

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4757-4774, 2025, DOI:10.32604/cmc.2025.063345 - 19 May 2025

Abstract This study presents a groundbreaking method named Expo-GAN (Exposition-Generative Adversarial Network) for style transfer in exhibition hall design, using a refined version of the Cycle Generative Adversarial Network (CycleGAN). The primary goal is to enhance the transformation of image styles while maintaining visual consistency, an area where current CycleGAN models often fall short. These traditional models typically face difficulties in accurately capturing expansive features as well as the intricate stylistic details necessary for high-quality image transformation. To address these limitations, the research introduces several key modifications to the CycleGAN architecture. Enhancements to the generator involve… More >

Qin Wang¹, Xiaofeng Wang^2,*, Jianghua Li², Ruidong Han², Zinian Liu¹, Mingtao Guo³

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4607-4621, 2025, DOI:10.32604/cmc.2025.063141 - 19 May 2025

Abstract The majority of current deepfake detection methods are constrained to identifying one or two specific types of counterfeit images, which limits their ability to keep pace with the rapid advancements in deepfake technology. Therefore, in this study, we propose a novel algorithm, Stereo Mixture Density Network (SMNDNet), which can detect multiple types of deepfake face manipulations using a single network framework. SMNDNet is an end-to-end CNN-based network specially designed for detecting various manipulation types of deepfake face images. First, we design a Subtle Distinguishable Feature Enhancement Module to emphasize the differentiation between authentic and forged… More >

Xuezhi Wen¹, Eric Danso^2,*, Solomon Danso²

Journal of Cyber Security, Vol.7, pp. 45-69, 2025, DOI:10.32604/jcs.2025.063606 - 08 May 2025

Abstract Deep learning models have achieved remarkable success in healthcare, finance, and autonomous systems, yet their security vulnerabilities to adversarial attacks remain a critical challenge. This paper presents a novel dual-phase defense framework that combines progressive adversarial training with dynamic runtime protection to address evolving threats. Our approach introduces three key innovations: multi-stage adversarial training with TRADES (Tradeoff-inspired Adversarial Defense via Surrogate-loss minimization) loss that progressively scales perturbation strength, maintaining 85.10% clean accuracy on CIFAR-10 (Canadian Institute for Advanced Research 10-class dataset) while improving robustness; a hybrid runtime defense integrating feature manipulation, statistical anomaly detection, and… More >

Jifeng Liang¹, Qiang Wang², Leibao Wang¹, Ziwei Zhang³, Yonghui Sun^3,*, Hongzhu Tao⁴, Xiaofei Li⁵

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.1, pp. 945-965, 2025, DOI:10.32604/cmes.2025.062315 - 11 April 2025

Abstract Wind power generation is subjected to complex and variable meteorological conditions, resulting in intermittent and volatile power generation. Accurate wind power prediction plays a crucial role in enabling the power grid dispatching departments to rationally plan power transmission and energy storage operations. This enhances the efficiency of wind power integration into the grid. It allows grid operators to anticipate and mitigate the impact of wind power fluctuations, significantly improving the resilience of wind farms and the overall power grid. Furthermore, it assists wind farm operators in optimizing the management of power generation facilities and reducing… More > Graphic Abstract

Nizar Zaghden¹, Emad Ibrahim², Mukaram Safaldin^2,*, Mahmoud Mejdoub³

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1117-1147, 2025, DOI:10.32604/cmc.2025.061948 - 26 March 2025

Abstract The increasing elderly population has heightened the need for accurate and reliable fall detection systems, as falls can lead to severe health complications. Existing systems often suffer from high false positive and false negative rates due to insufficient training data and suboptimal detection techniques. This study introduces an advanced fall detection model integrating YOLOv8, Faster R-CNN, and Generative Adversarial Networks (GANs) to enhance accuracy and robustness. A modified YOLOv8 architecture serves as the core, utilizing spatial attention mechanisms to improve critical image regions’ detection. Faster R-CNN is employed for fine-grained human posture analysis, while GANs… More >

Xiaoyin Yi^1,2, Long Chen^1,3,4,*, Jiacheng Huang¹, Ning Yu¹, Qian Huang⁵

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 157-175, 2025, DOI:10.32604/cmc.2025.059863 - 26 March 2025

Abstract Transfer-based Adversarial Attacks (TAAs) can deceive a victim model even without prior knowledge. This is achieved by leveraging the property of adversarial examples. That is, when generated from a surrogate model, they retain their features if applied to other models due to their good transferability. However, adversarial examples often exhibit overfitting, as they are tailored to exploit the particular architecture and feature representation of source models. Consequently, when attempting black-box transfer attacks on different target models, their effectiveness is decreased. To solve this problem, this study proposes an approach based on a Regularized Constrained Feature More >

Mariam Ishtiaq^1,2, Jong-Un Won^1,2,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5343-5361, 2025, DOI:10.32604/cmc.2025.061466 - 06 March 2025

Abstract Fire detection has held stringent importance in computer vision for over half a century. The development of early fire detection strategies is pivotal to the realization of safe and smart cities, inhabitable in the future. However, the development of optimal fire and smoke detection models is hindered by limitations like publicly available datasets, lack of diversity, and class imbalance. In this work, we explore the possible ways forward to overcome these challenges posed by available datasets. We study the impact of a class-balanced dataset to improve the fire detection capability of state-of-the-art (SOTA) vision-based models and propose… More >

Yuqiao Liu¹, Chen Pan¹, YeonJae Oh^2,*, Chang Gyoon Lim^1,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4593-4629, 2025, DOI:10.32604/cmc.2025.061196 - 06 March 2025

Abstract Virtual Power Plants (VPPs) are integral to modern energy systems, providing stability and reliability in the face of the inherent complexities and fluctuations of solar power data. Traditional anomaly detection methodologies often need to adequately handle these fluctuations from solar radiation and ambient temperature variations. We introduce the Memory-Enhanced Autoencoder with Adversarial Training (MemAAE) model to overcome these limitations, designed explicitly for robust anomaly detection in VPP environments. The MemAAE model integrates three principal components: an LSTM-based autoencoder that effectively captures temporal dynamics to distinguish between normal and anomalous behaviors, an adversarial training module that… More >

Zhengshun Fei^1,*, Jianxin Chen¹, Gui Chen², Xinjian Xiang^1,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4237-4261, 2025, DOI:10.32604/cmc.2025.059262 - 06 March 2025

Abstract Tag recommendation systems can significantly improve the accuracy of information retrieval by recommending relevant tag sets that align with user preferences and resource characteristics. However, metric learning methods often suffer from high sensitivity, leading to unstable recommendation results when facing adversarial samples generated through malicious user behavior. Adversarial training is considered to be an effective method for improving the robustness of tag recommendation systems and addressing adversarial samples. However, it still faces the challenge of overfitting. Although curriculum learning-based adversarial training somewhat mitigates this issue, challenges still exist, such as the lack of a quantitative… More >