Deepfake Detection using Mamba

Abstract—Deepfake technology, driven by generative adversarial networks (GANs), poses significant challenges in digital security, misinformation, and privacy. Detecting deepfakes in images and videos requires advanced deep learning models. This study explores deepfake detection using convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based architectures like Vision Transformers (ViTs). We employ Meso4_DF deepfake detection pipeline that uses TensorFlow/Keras, PyTorch, OpenCV for processing, with Dlib, Scikit-Image, and NumPy for feature extraction, leveraging transfer learning for enhanced accuracy. Video analysis includes frame extraction and temporal feature learning using LSTMs and 3D CNNs. Experimental results demonstrate that deep learning-based methods achieve high accuracy in distinguishing real and manipulated media, offering a robust approach to deepfake detection. Keywords—Deepfake Detection,CNN,GAN,Meso4 model, Image Analysis,Video Analysis.

Abstract— The emergence of deepfake technology has improved exponentially and this intensified the fears that surround the credibility of audio recordings, in instance telecommunication and security. This project proposes a full deep learning-based approach to deepfake voice recordings detection in call communications as an improvement to the voice authentication processes used. It is with this in mind that we came up with an adaptive architecture that positions convolutional neural networks (CNN) and recurrent neural network (RNN) in a way that assists in distinguishing between real and fabricated sounds. The nature of the problem allows the use of a large amount of data collected from a wide variety of real and fake audio samples which serve for proper training and testing of the system. To improve the performance of the model, some strategies have been implemented including audio preprocessing such as spectrogram and features. This research adds to the existing body of literature on voice authentication but also seeks to underscore the need for solutions that secure audio communication in times when deepfakes are on the rise. Subsequent research will be dedicated to perfecting the existing model and assessing the feasibility of its use in practice. Keywords— Deepfake Detection, Voice Authentication, Synthetic Speech Analysis, Speech Forensics, Audio Deepfake Identification, MFCCs, Spectrogram Analysis, CNNs, RNNs, Transformer Models, Automatic Speaker Verification (ASV), AI Security, Fraud Prevention, Adversarial Attacks, Machine Learning for Audio Forensics.

Recent experience in applying recurrent neural networks (RNNs) to interpreting Permannt Downhole Gauge (PDG) records has highlighted the potential utility of machine learning algorithms to learn reservoir behavior from data. The power of the RNN resides in its ability to retain information in a form of memory of previous patterns and information contained in the previous behavior of phenomena being modeled. This memory plays a role of informing the decision at the present time by using what happened in the past. This property suggests RNNs as a suitable choice to model sequences of reservoir information, even when the reservoir modeler is faced with incomplete knowledge of the underlying physical system. Convolutional Neural Networks (CNNs) are another variant of machine learning algorithms that have shown promise in sequence modeling domains, such as audio synthesis and machine translation. In this study, RNN and CNN were applied to tasks that traditionally would be modeled by a reservoir simulator. This was achieved by formulating the relationship between physical quantities of interest from subsurface reservoirs as a sequence mapping problem. In addition, the performance of a CNN layer as compared to RNN was evaluated systematically to investigate their capabilities in a variety of tasks of interest to the reservoir engineer. Preliminary results suggest that CNNs, with specific design modifications, are as capable as RNNs in modeling sequences of information and as reliable when making inferences to cases that has not been seen by the algorithm during training. Design details and reasons pertaining to the way these two seemingly different architectures process information, and handle memory are also discussed.

Deepfakes, which are synthetic media realistic in nature generated using artificial intelligence (AI); pose a significant threat to individuals and society. The rapid advancement of deepfake technology has led to the creation of highly realistic synthetic content covering images, videos, audio, and news. While deepfake applications offer creative possibilities, their misuse for misinformation, identity fraud, and cybersecurity threats necessitates robust detection methods. Deepfake crimes are rising daily, wherein deepfake media detection has become a big challenge and has high claim in digital forensics. This review explores the state-of-the-art deep learning (DL) techniques for deepfake detection of four parameters, namely images, videos, audio, and news. The ML approaches rely on handcrafted features but struggle with evolving deepfake methods. In contrast, DL techniques, such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, have demonstrated superior detection accuracy by learning discriminative features. Even Recurrent Neural Networks (RNNs), and Transformer-based architectures like Bidirectional encoder representations from transformers (BERT), have demonstrated superior accuracy in identifying manipulated content. Furthermore, recent advancements such as Vision Transformers (ViTs) and Explainable AI (XAI) models are enhancing detection interpretability and robustness. This review highlights the future research directions for strengthening deepfake detection mechanisms. The rapid advancements in deepfake generation necessitate continuous research and development of countermeasures.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

A hybrid model based on neural networks for biomedical relation extraction

Deep fakes, synthetic media generated through artificial intelligence (AI) techniques, have become a growing concern due to their potential for misinformation, manipulation, and security threats. As the sophistication of deep fake technology continues to evolve, traditional methods of detection are becoming less effective, thus prompting the need for advanced AI-driven solutions. This article explores the various AI techniques employed in deep fake detection, such as deep learning, neural networks, and computer vision algorithms. A review of the latest advancements in AI technologies, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs), is presented to highlight their roles in identifying deep fakes. Additionally, we explore challenges related to data availability, model robustness, and ethical implications. The paper concludes by proposing a hybrid detection framework that integrates multiple AI techniques to enhance the accuracy and efficiency of deep fake identification.

Transformer is a kind of deep neural network that relies on the technique of self-attention and used initially in the field of natural language processing. Scientists use transformer for computer vision (CV) applications because of its good data representation capabilities. Transformer-based models yield similar performance or surpass other network architectures, including convolutional and recurrent neural networks, in a variety of visual benchmarks. In this work, we investigate the methods for video anomaly detection (VAD) using vision transformer models in the recent literature. The main topics we explore comprise vision transformers used in CV applications with a special focus on VAD methods leveraging transformer architecture. We also briefly present anomaly detection methods based on transformers. Additionally, we address the advantages, challenges and current limitations of the transformer architecture as well as potential solutions to address the technical challenges. In the concluding section of this study, we offer avenues for further investigation concerning the use of vision transformers in VAD tasks.

Deep learning (DL) has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data. A number of comprehensive reviews have been published on such applications, ranging from high-level reviews with future perspectives to those mainly serving as tutorials. These reviews have provided an excellent introduction to and guideline for applications of DL in bioinformatics, covering multiple types of machine learning (ML) problems, different DL architectures, and ranges of biological/biomedical problems. However, most of these reviews have focused on previous research, whereas current trends in the principled DL field and perspectives on their future developments and potential new applications to biology and biomedicine are still scarce. We will focus on modern DL, the ongoing trends and future directions of the principled DL field, and postulate new and major applications in bioinformatics.

The rapid advancement of digital content generation technologies has led to the proliferation of deepfake media, posing significant security and privacy risks on social networks. Conventional deepfake detection methods struggle with accuracy, computational efficiency, and adaptability to evolving fake image generation techniques. To address these challenges, we propose a novel deepfake detection framework that integrates an Adaptive deep convolutional generative adversarial network (Adaptive-DCGAN) with a lightweight convolutional neural network (Lite-CNN). The Adaptive-DCGAN generates high-quality synthetic images, enhancing the training dataset, while the Lite-CNN efficiently classifies real and fake images with minimal computational overhead. Experimental results demonstrate that the proposed model achieves 95% accuracy, significantly outperforming existing GAN-CNN-based detection systems, which only reach 53% accuracy. Additionally, the framework exhibits superior performance metrics, including 95% precision, recall, and F1-score, ensuring robust and reliable deepfake detection. The proposed system offers a scalable and efficient solution for securing digital media platforms against deepfake threats. Future work will focus on improving generalization across diverse datasets, incorporating advanced synthetic image generation techniques, and enabling real-time deepfake detection for large-scale social media applications.

The expansion of digital media in recent years has created an immediate need for automated systems for reliable detection of obscene content. Such systems are essential for safeguarding users, upholding ethical standards, and ensuring compliance with regulatory frameworks. This paper surveys recent advances in deep learning methods, particularly convolutional neural networks (CNNs), recurrent neural networks (RNNs), and emerging transformer-based and vision–language models. We emphasize how these approaches are integrated within engineering frameworks, ranging from distributed cloud pipelines to edge deployments, to support large-scale content moderation. The reviewed methods demonstrate strong capabilities in learning complex visual and contextual patterns, leading to high performance in tasks such as obscene image and video classification. Computational strategies that improve accuracy, precision, recall, F1-score, AUC, and real-time latency are highlighted, along with challenges of scalability, dataset bias, adversarial attacks, and resource constraints. By combining technical insights with discussions of ethical and privacy considerations, this review proposes a multidisciplinary framework for building more precise, fair, and resilient obscenity detection systems. The work serves as a practical reference for engineers, developers, and policymakers while outlining open challenges and future opportunities, including multimodal moderation, deepfake detection, and privacy-preserving learning approaches.

To analyse the DeepFakes, which are AI-generated synthetic media that impersonate real people and pose substantial threats to digital content security, privacy, and authenticity. This research investigates a unique technique to DeepFake detection that employs Recurrent neural networks (RNN) are used for temporal sequence analysis and convolutional neural networks (CNN) for extracting spatial features. The suggested method seeks to improve detection accuracy across a wide range of DeepFake datasets by combining the strengths of CNNs and RNNs. The experimental results show that this hybrid architecture is excellent at identifying DeepFakes with good precision and recall.)

Altered and manipulated multimedia is increasingly present and widely distributed via social media platforms. Advanced video manipulation tools enable the generation of highly realistic-looking altered multimedia. While many methods have been presented to detect manipulations, most of them fail when evaluated with data outside of the datasets used in research environments. In order to address this problem, the Deepfake Detection Challenge (DFDC) provides a large dataset of videos containing realistic manipulations and an evaluation system that ensures that methods work quickly and accurately, even when faced with challenging data. In this paper, we introduce a method based on convolutional neural networks (CNNs) and recurrent neural networks (RNNs) that extracts visual and temporal features from faces present in videos to accurately detect manipulations. The method is evaluated with the DFDC dataset, providing competitive results compared to other techniques.

Modeling accurate text recognizers for scanned Devanagari scripts is a challenging task, primarily due to the ingrained complexities of characters, vowels, conjuncts, and modifiers in the word formation of the script. This paper presents an attention-based convolutional recurrent neural network (CRNN) for improving the text recognition accuracy of the Devanagari script images. The proposed model is an encoder–decoder network with an attention mechanism. The encoder is a convolutional neural network (CNN), which extracts the significant and high-level features from the input images. The encoder also generates the extracted features in an ordered sequence. The decoder uses a bidirectional long short-term (BLSTM) network with an attention mechanism, followed by a connectionist temporal classification (CTC) layer to predict the text in images. The attention mechanism enables the decoder to selectively exploit the high-level features of the encoder congruently. We have trained, validated, and tested the performance of the proposed model on three datasets, viz. publicly available IIIT-H scene image dataset, synthetic dataset, and real dataset curated during this work. We have also compared the proposed model results with work already attempted in the area for the three datasets. We found that the performance of our proposed model outdoes the outcomes obtained from other models on the three datasets.

- Deepfakes are artificially generated multimedia content that can convincingly mimic real human faces and voices using advanced AI techniques such as Generative Adversarial Networks (GANs). This poses serious ethical, social, and security challenges in digital communication. To address this issue, the proposed project presents a Multimodal Deepfake Detection System that integrates image, video, and audio analysis pipelines within a unified framework. The system employs Efficient Net-based CNN for image forgery detection, CNN combined with Bi-LSTM for temporal video analysis, and a 1D-CNN with LSTM for detecting manipulated or cloned audio. The predictions from these modalities are combined using a Fuzzy Fusion Engine, which intelligently weights each confidence score to produce a final verdict with high accuracy and interpretability. The model is trained using public Deepfake datasets such as Face Forensics++, Celeb-DF, and DFDC, with binary cross-entropy loss, data augmentation, and early stopping to ensure stable convergence and better generalization. The trained models are deployed on Hugging Face Spaces, while the web interface is hosted on Vercel, enabling real-time Deepfake detection for users through a browser interface. This approach enhances detection accuracy by leveraging multimodal evidence (visual, temporal, and auditory), improves generalization across datasets, and provides an explainable and efficient solution to combat the growing threat of Deepfakes. Key Words: Deepfake Detection, Multimodal Learning, Bi-LSTM, Fuzzy Fusion, Convolutional Neural Network (CNN), Face Forensics++, Celeb DF, DFDC, Machine Learning, Real-Time Detection, Hugging Face.