Jul 2026· American Journal of AI Cyber Computing Management· 0 citations· 6 references
TL;DR
This project presents an explainable deep learning framework for identifying real and AI-generated images using the NASNet architecture and achieves high detection accuracy while providing interpretable visual explanations, making it suitable for digital image verification, media authentication, and cybersecurity applications.
Abstract
The rapid growth of generative artificial intelligence has made it easier to create highly realistic synthetic images, increasing the risk of misinformation, identity misuse, and digital fraud. Distinguishing AI-generated images from authentic ones has become a significant challenge due to their visual similarity. This project presents an explainable deep learning framework for identifying real and AI-generated images using the NASNet architecture. The model is trained on a balanced dataset containing genuine and synthetic face images after applying preprocessing techniques such as resizing, normalization, and data shuffling. To improve transparency, the system integrates Explainable AI (XAI) methods, including Grad-CAM and LIME, which highlight the image regions that influence the model’s predictions. A web-based interface enables users to upload images in different formats and receive instant classification results. Experimental evaluation demonstrates that the proposed approach achieves high detection accuracy while providing interpretable visual explanations, making it suitable for digital image verification, media authentication, and cybersecurity applications.
Experimental results demonstrate that the proposed approach effectively identifies deepfake images with high accuracy, making it suitable for applications in digital forensics, media verification, and cybersecurity.
J. Kollu, Mortha Pavan, Putta Vardhan et al.· International Journal of Inn...· 0 citations
The proposed Attention-Based Deep Learning Pipeline of AI-Created Image Recognition incorporates three integrated branches, including low-level statistical feature extraction, high-level semantic representation learning, and attention-based feature refinement mechanism, which support the robustness and generalization ability of the proposed model in detecting AI-generated images in a variety of generators and conditions.
Nadia Ali· Al-Noor Journal of Engineeri...· 0 citations
The ability of Generative Adversarial Networks (GANs) to produce images that closely resemble real ones has raised concern. This requires the creation of efficient detection techniques because it has significant ramifications for digital media, security, and ethics. In order to demonstrate the growing difficulties of attaining authenticity in the rapidly developing field of Artificial Intelligence (AI), this study introduces this critical issue by leveraging the “Detect AI-Generated Faces: High-Quality Dataset,” obtained from Kaggle which contains 3,203 images of real human faces and AI-generated faces. However, the Orange3 data mining framework is used to analyze these images, focusing on extracting essential features such as shape attributes, texture descriptors, and color histograms. The dataset was divided into a training set (70%) and a testing set (30%) to evaluate our models effectively. Also, four machine learning algorithms were employed: K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Adaptive Boosting (AdaBoost), and Gradient Boosting (GB). The results revealed that KNN and AdaBoost achieved impressive accuracies of 99.4% and 97.07%, respectively, while GB and ANN reached even higher accuracies of 99.8% and 99.9%. These results underscore the effectiveness of advanced machine learning techniques in accurately distinguishing between AI-generated and real faces.
Areen Arabiat· International Journal of Ele...· 16 citations
ABSTRACT
The rapid advancement of generative artificial intelligence has led to the widespread creation of highly realistic synthetic images. While these technologies have many beneficial applications, they also introduce challenges such as misinformation, identity fraud, copyright violations, and digital manipulation. This project proposes a Convolutional Neural Network (CNN)-based system to distinguish AI-generated images from authentic photographs. To improve transparency and trust in the model's decisions, Explainable Artificial Intelligence (XAI) techniques such as Grad-CAM, LIME, or SHAP are integrated to visualize the image regions that influence the classification. The proposed system aims to achieve high detection accuracy while providing interpretable explanations for each prediction.
B. Kumari, Kovvuri Himalakshmi· International Scientific Jou...· 0 citations
The rapid growth of artificial intelligence has led to the development of advanced technologies capable of generating highly realistic fake images and videos, commonly known as deepfakes. Although these technologies have useful applications in entertainment, education, and digital media, they can also be misused for spreading misinformation, identity theft, fraud, and other cybercrimes. This paper presents an AI-based fake image and video detection system using deep learning models such as InceptionV3, EfficientNet, and a Hybrid model. The proposed system preprocesses input images and video frames through resizing, normalization, and data augmentation to improve model performance. The trained models extract meaningful visual features and classify the uploaded media as real or fake. The Hybrid model combines the strengths of InceptionV3 and EfficientNet to achieve improved feature extraction and higher classification accuracy. The performance of the proposed system is evaluated using standard metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that the Hybrid model outperforms the individual models in detecting manipulated media. The proposed approach provides an efficient, accurate, and reliable solution for identifying AI-generated content and helps improve the authenticity, security, and trustworthiness of digital media across various online platforms.
Vidyashree H R and Dr. Manjunath B· International Journal of Adv...· 0 citations
This review presents a comprehensive analysis of recent deep learning and transfer learning techniques for fake image detection, examining widely adopted convolutional neural network architectures, benchmark datasets, evaluation metrics, and current research developments.
Nisha Parveen, Anjali Saxena· International Journal for Re...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
