DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learning

Zobaed, SM; Rabby, Fazle; Hossain, Istiaq; Hossain, Ekram; Hasan, Sazib; Karim, A. K. M. Rezaul; Hasib, Khan Md.

doi:10.1007/978-3-030-88040-8_7

Cited by 15 publications

(3 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To classify sentence level, CNN is employed in this study [19] to conduct a series of experiments, training on the uppermost of pre-trained word vectors. A simple CNN architecture can be hyperparameter tuned to upgrade performance [20]. Authors showed that, using fine-tuning approach, task-specific vectors can aid to improve classification accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data

Hasib,

Azam,

Karim

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Searching, retrieving, and arranging text in ever-larger document collections necessitate more efficient information processing algorithms. Document categorization is a crucial component of various information processing systems for supervised learning. As the quantity of documents grows, the performance of classic supervised classifiers has deteriorated because of the number of document categories. Assigning documents to a predetermined set of classes is called text classification. It is utilized extensively in a wide range of data-intensive applications. However, the fact that real-world implementations of these models are plagued with shortcomings begs for more investigation. Imbalanced datasets hinder the most prevalent high-performance algorithms. In this paper, we propose an approach name multi-class Convolutional Neural Network (MCNN)-Long Short-Time Memory (LSTM), which combines two deep learning techniques, Convolutional Neural Network (CNN) and Long Short-Time Memory, for text classification in news data. CNN's are used as feature extractors for the LSTMs on text input data and have the spatial structure of words in a sentence, paragraph, or document. The dataset is also imbalanced, and we use the Tomek-Link algorithm to balance the dataset and then apply our model, which shows better performance in terms of F1-score (98%) and Accuracy (99.71%) than the existing works. The combination of deep learning techniques used in our approach is ideal for the classification of imbalanced datasets with underrepresented categories. Hence, our method outperformed other machine learning algorithms in text classification by a large margin. We also compare our results with traditional machine learning algorithms in terms of imbalanced and balanced datasets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data

Hasib,

Azam,

Karim

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DeepFakes detection is primarily focused on identifying and combating the spread of fake news and misinformation [115,70,116,59]. The current surveys can help prevent the potential harm caused by the misuse of DeepFakes and ensure that the information presented is accurate and trustworthy [106,50].…”

Section: Related Surveysmentioning

confidence: 99%

GAN-Generated Faces Detection: A Survey and New Perspectives

Wang,

Guo,

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts. Therefore, the corresponding GAN-face detection techniques are under active development that can examine and expose such fake faces. In this work, we aim to provide a comprehensive review of recent progress in GAN-face detection. We focus on methods that can detect face images that are generated or synthesized from GAN models. We classify the existing detection works into four categories: (1) deep learning-based, (2) physical-based, (3) physiological-based methods, and (4) evaluation and comparison against human visual performance. For each category, we summarize the key ideas and connect them with method implementations. We also discuss open problems and suggest future research directions.

show abstract

“…Deep learning is a practical and efficient technique that has been widely applied in various domains, including computer vision and NLP. It has revolutionized these fields by enabling machines to learn and make predictions from large amounts of data [1]. Deepfake becomes harder to distinguish between actual and fake information.…”

Section: Introductionmentioning

confidence: 99%

Explainable Deep Fake Framework for Images Creation and Classification

Alwateer

2024

JCC

View full text Add to dashboard Cite

Deep learning is a practical and efficient technique that has been used extensively in many domains. Using deep learning technology, deepfakes create fake images of a person that people cannot distinguish from the real one. Recently, many researchers have focused on understanding how deepkakes work and detecting using deep learning approaches. This paper introduces an explainable deepfake framework for images creation and classification. The framework consists of three main parts: the first approach is called Instant ID which is used to create deepfacke images from the original one; the second approach called Xception classifies the real and deepfake images; the third approach called Local Interpretable Model (LIME) provides a method for interpreting the predictions of any machine learning model in a local and interpretable manner. Our study proposes deepfake approach that achieves 100% precision and 100% accuracy for deepfake creation and classification. Furthermore, the results highlight the superior performance of the proposed model in deep fake creation and classification.

show abstract

DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learning

Cited by 15 publications

References 72 publications

MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data

MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data

GAN-Generated Faces Detection: A Survey and New Perspectives

Explainable Deep Fake Framework for Images Creation and Classification

Contact Info

Product

Resources

About