Deepfakes pose a serious threat to media authenticity and public trust. This paper proposes a hybrid deep learning model combining ResNeXt and LSTM to detect deepfakes by capturing both spatial and temporal inconsistencies. ResNeXt extracts detailed frame-level features, while LSTM models temporal dependencies across video frames. Evaluated on benchmark datasets such as DFDC and Celeb-DF, the model achieves high accuracy and robust performance. The results confirm that integrating spatial and temporal features significantly improves deepfake detection, offering a reliable approach for video-based forensic analysis.
| Mualliflar | primbetov, abbaz, Maxmudjanov, Sarvar, Naimov , Axadjon |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2025-06-03 |
| Son | 2 |
| Betlar | 87-94 |
| Til | Rus |
Resnext, LSTM, Deepfake.
This аrticle discusses the issues оf building secure netwоrks bаsed оn VPN (Virtuаl Privаte Netwоrk) technоlоgy in mоdern enterprise аnd оrgаnizаtiоnаl infоrmаtiоn аnd cоmmunicаtiоn systems. The pаper exаmines the mаin…
This article analyzes cryptographic algorithms based on elliptic curves (ECC) and their effectiveness. The main complexity of ECC is due to the difficulty of solving the discrete logarithm problem, which provides a high…
Deepfake technology, driven by advancements in artificial intelligence (AI) and deep learning, facilitates the creation of hyper-realistic synthetic media—encompassing images, videos, and audio. While this innovation…
Annotatsiya: Axborot-kommunikatsiya texnologiyalarining jadal rivojlanishi sud-biologik ekspertizalarda DNK asosidagi bog'lanish jarayonlarini raqamlashtirish va avtomatlashtirish ishlari. olingan, ota-ona va…
This article proposes an approach for detecting and identifying Stuxnet-type cyberattacks in modern Internet of Things (IoT) systems. A model of informative features has been developed, and a knowledge base for…
Today, interest in the use of renewable energy sources, particularly solar energy, is growing globally. Due to global climate change, the depletion of traditional energy resources, and the pursuit of environmental…
Tabiat hududlarining vegetatsiya holatini vizualizatsiya qilish usuli, yerga yaqin sun’iy yo‘ldoshlar yordamida o‘rmonlarni monitoring qilishning eng yaxshi yechimi hisoblanadi. Uzoq masofadan sezish natijalarini…
This article is devoted to the analysis of the dynamic model of Use Management, the formal specification and algorithms in the dynamic model, and the description of the developed use roll restriction system model…
This article are presented algorithms for formalization, digitization and analysis of nominal data. This article proposes methods and algorithms for reducing the dimensionality of the original feature space of…
Abstract: This article analyzes the experiences of implementing automated class scheduling systems in the education systems of Uzbekistan and developed countries. As a result of the widespread use of information…