The rapid rise in the use of artificially generated faces has significantly increased the risk of identity theft in biometric authentication systems. Modern facial recognition technologies are now vulnerable to sophisticated attacks using printed images, replayed videos, and highly realistic 3D masks. This creates an urgent need for advanced, reliable, and mobile-compatible fake face detection systems. Research indicates that while deep learning models have demonstrated strong performance in detecting artificially generated faces, deploying these models on consumer mobile devices remains challenging due to limitations in computing power, memory, privacy, and processing speed. This paper highlights several key challenges: (1) optimizing deep learning models to operate efficiently on mobile devices, (2) ensuring real-time inference without compromising accuracy, (3) maintaining user privacy when processing sensitive facial data, and (4) addressing the variability in mobile phone cameras, input resolution, and platform limitations across Android and iOS. Furthermore, the increasing sophistication of identity spoofing attacks—such as 3D masks and AI-generated faces—demands more sophisticated, robust, and multimodal detection technologies. The research findings provide a clear roadmap toward practical solutions. By evaluating the latest deep learning architectures, datasets, and anti-spoofing metrics, the study proposes a comprehensive React Native deployment path using TensorFlow Lite and TensorFlow.js to ensure cross-platform compatibility. The proposed system offers a unified classification of identity spoofing attacks and defense mechanisms, along with a structured evaluation framework that compares on-device processing with server-side detection. The results demonstrate that optimized models can achieve high accuracy, low false accept/rejection rates, and sub-second processing speeds on mobile devices. Ultimately, the study provides practical design guidelines for building robust, privacy-preserving, efficient, and real-world consumer-grade fake face detection systems.
Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the bes
... Show Morein this paper we adopted ways for detecting edges locally classical prewitt operators and modification it are adopted to perform the edge detection and comparing then with sobel opreators the study shows that using a prewitt opreators
Most Internet-tomography problems such as shared congestion detection depend on network measurements. Usually, such measurements are carried out in multiple locations inside the network and relied on local clocks. These clocks usually skewed with time making these measurements unsynchronized and thereby degrading the performance of most techniques. Recently, shared congestion detection has become an important issue in many computer networked applications such as multimedia streaming and
peer-to-peer file sharing. One of the most powerful techniques that employed in literature is based on Discrete Wavelet Transform (DWT) with cross-correlation operation to determine the state of the congestion. Wavelet transform is used as a de-noisin
This study aimed to investigate the prevalence of intestinal helminth infections in humans and detect Toxocara spp. in cats, with a focus on assessing the impact of age and gender on infection rates. Traditional diagnostic methods have historically limited the accurate identification of helminth infections in humans. Analysis of 450 human stool samples revealed an overall helminth infection rate of 5.7% using conventional techniques. The specific infection rates were 0.4% for Strongyloides stercoralis, 0.6% for Schistosoma mansoni, 1.7% for Hymenolepis nana, and 2.8% for Ascaris lumbricoides. Notably, no infections were recorded in the 30–39 and ≥40-year age groups, while the highest infection rate (16.3%, P≤0.01) was observed in indi
... Show More The present study is an attempt for detection of A. baumannii by conventional and PCR methods using species-specific primers for these A. baumannii. A total of 87 samples were collected from hospitals in Baghdad (Al-Rasafa and Al-Karkh Hospitals) during the period from 2019 to 2020.The samples included: 40 specimens, from wounds, respiratory infections (sputum), burns, CSF and 47 samples from the hospital environment (swabs), while samples collected from intensive care unit including patient beds, surgical instruments and appliances, emergency lobby and baby incubators. A. baumannii isolate identification depending on the morphologic characteristics on the culture media including, blood agar, MacConkey agar, as well as t
... Show More