Article
Computer Science, Information Systems
Feng Ding, Guopu Zhu, Yingcan Li, Xinpeng Zhang, Pradeep K. Atrey, Siwei Lyu
Summary: The study shows that DeepFake technology may pose a potential threat, so researchers are working on developing anti-forensics methods. The GAN model proposed in this paper can effectively combat DeepFake forensics detectors, generate high-quality anti-forensics videos, significantly boosting the level of DeepFake anti-forensics.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Asad Malik, Minoru Kuribayashi, Sani M. Abdullahi, Ahmad Neyaz Khan
Summary: This article provides an overview of DeepFake detection methods for face images and videos, summarizes the types of DeepFake creation techniques, and discusses the trends in DeepFake datasets. Additionally, it analyzes the general DeepFake detection model and the challenges associated with DeepFake creation and detection.
Article
Computer Science, Software Engineering
Gaoming Yang, Kun Xu, Xianjin Fang, Ji Zhang
Summary: Deep learning advancements have led to breakthroughs in facial forgery techniques, making it difficult to distinguish between real and fake videos. This study proposes an approach that extracts and analyzes features from both real and forged material to detect video face forgery. The use of a unique facial double-triangle region assists in capturing dense optical flow truncation and the proposed approach shows promising results in detecting video face forgery.
Article
Computer Science, Information Systems
Marriam Nawaz, Ali Javed, Aun Irtaza
Summary: The great development in AI has brought advancements in information technology. Lightweight ML techniques allow limited storage and processing power. Deepfakes, a famous application of this era, poses serious risks to global security and confidentiality. Detecting and classifying deepfakes accurately is challenging due to convincingly manipulated content produced by GANs. This study proposes a DL-based approach called C-LSTM for deepfakes detection, utilizing pre-trained models like VGG16, VGG19, ResNet50, XceptionNet, GoogleNet, and DenseNet, as well as a novel feature descriptor called Dense-Swish-Net121. Results show that the proposed Dense-Swish-Net121 with Bi-LSTM approach performs well in deepfakes detection.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Qingwen Li, Jianni Chen, Qiqin Xie, Xiao Han
Summary: Video summarization plays a crucial role in the era of online videos. This paper proposes an efficient Boundary-Aware framework for Summary clip Extraction (BASE) to extract summary clips of more important events in videos with precise boundaries and complete content.
Article
Computer Science, Artificial Intelligence
Gioele Ciaparrone, Leonardo Chiariglione, Roberto Tagliaferri
Summary: This article presents an end-to-end face-based video retrieval (FBVR) pipeline that can handle large datasets of multi-shot, multi-person videos. By comparing various deep learning models for different tasks, a high-performing pipeline is proposed and achieves a high accuracy rate in experiments.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Chemistry, Analytical
Yun Gu Lee, Gihyun Na, Junseok Byun
Summary: Video is important evidence in digital forensics, but it can be easily tampered with. This paper presents a new method for detecting double-compressed videos using the descriptors of video encoders. The method detects the changes in the descriptor of the test video to identify double-compressed videos.
Article
Automation & Control Systems
Abdul Rehman Javed, Zunera Jalil, Wisha Zehra, Thippa Reddy Gadekallu, Doug Young Suh, Md Jalil Piran
Summary: This paper presents a comprehensive survey on information extraction from video contents and forgery detection, reviewing various modern techniques such as computer vision and different machine learning algorithms, including deep learning for video forgery detection.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Minh Dang
Summary: This study introduces a large face manipulation dataset and trains a fine-tuned RegNet model to effectively detect manipulated face images. The study also implements a manipulated region analysis technique for in-depth insights into the manipulated regions.
Article
Computer Science, Information Systems
Gaojian Wang, Qian Jiang, Xin Jin, Xiaohui Cui
Summary: DeepFakes are prevalent on social networks and pose significant information concerns. Existing detection methods face practical limitations and high costs, and often lack generalizability under cross-dataset scenarios. In this study, we propose a lightweight and fast detection method that leverages the subtle and generalized defects of DeepFakes, achieving promising results.
INFORMATION SCIENCES
(2022)
Review
Computer Science, Information Systems
Saima Waseem, Syed Abdul Rahman Syed Abu Bakar, Bilal Ashfaq Ahmed, Zaid Omar, Taiseer Abdalla Elfadil Eisa, Mhassen Elnour Elneel Dalam
Summary: This article discusses the advancements in deep learning that have led to the creation of highly realistic AI-generated videos known as deepfakes. The article examines existing methods of creating deepfake images and videos and provides an overview of publicly available deepfake datasets. It also explores the detection approaches used to identify deepfake face and expression swaps and outlines future research directions in deepfake detection methods.
Article
Computer Science, Artificial Intelligence
Rosa Gil, Jordi Virgili-Goma, Juan-Miguel Lopez-Gil, Roberto Garcia
Summary: This study conducts a bibliometric analysis of articles on the evolution and trends of deepfakes technology. It answers six research questions and identifies 331 research articles on deepfakes. The analysis provides insights on research areas, current topics, trends, researchers, and funding institutions in the field of deepfakes. This paper presents current trends and opportunities for practitioners and researchers interested in deepfakes research.
Article
Computer Science, Information Systems
Fatma Ben Aissa, Monia Hamdi, Mourad Zaied, Mahmoud Mejdoub
Summary: Image source forensics is considered an effective method for verifying the authenticity and integrity of digital images. A recent topic in this field is the detection of DeepFakes generated by GANs. With the rapid growth of GANs, it has become easier to generate realistic images that are difficult to distinguish from real ones. Therefore, detecting DeepFakes created by GANs is important.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Thanh Thi Nguyen, Quoc Viet Hung Nguyen, Dung Tien Nguyen, Duc Thanh Nguyen, Thien Huynh-The, Saeid Nahavandi, Thanh Tam Nguyen, Quoc-Viet Pham, Cuong M. Nguyen
Summary: This paper discusses the issue of Deepfake, which can create fake images and videos. It presents the algorithms used to create Deepfake and methods proposed in the literature to detect Deepfake. Furthermore, it provides extensive discussions on the challenges, research trends, and directions related to Deepfake technologies.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2022)
Article
Computer Science, Information Systems
Staffy Kingra, Naveen Aggarwal, Nirmal Kaur
Summary: The authenticity of digital content is questioned due to the widespread availability of easy-to-use content editing software and deepfake technology. This paper surveys video integrity verification techniques and focuses on emerging deepfake video detection methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)