Deep Fake Detection Using Computer Vision-Based Deep Neural Network with Pairwise Learning

Ram, R. Saravana; Kumar, Mithilesh; Al-shami, Tareq M.; Masud, Mehedi; Aljuaid, Hanan; Abouhawwash, Mohamed

doi:10.32604/iasc.2023.030486

Cited by 9 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x Data set: In the proposed method different data sets (wild deep fake [10] CELEB-DF (V2) data set [11], Face Forensics++ data set [12], and) used to train and test the images from these data sets. x Preprocessing: Before utilization for model training and inference, it is essential that images undergo initial preprocessing.…”

Section: Methodsmentioning

confidence: 99%

A Deep Fake Detection System Using Diffusion Model Based on Graph Based Image Segmentation

Al-Din,

Jaber,

Mahan

2023

Machine Learning and Artificial Intelligence

View full text Add to dashboard Cite

With the development of technology and the increase in the need to use the internet and the transmission of personal data and save it on the cloud and personal computers and with the increase in security risks represented by penetrations and cyber threats, and among these threats are those represented by the use of deep learning techniques to produce deep fake images that are mostly used to violate cyber security through threats such as the ransom threat or publishing fake news and other cyber risks, so there was an urgent need to establish systems to detect deep forgery in images or videos, in this paper a system was proposed to detect deep forgery based on the principle of using the diffusion model based on the graph based on image segmentation where the system transforms the image to graph and then segment it into three areas which are fake, real and background. And do purification of the adversarial content in these areas using diffusion technology, and then identify the fake areas in the image and use GCN in order to distinguish between real and fake images. In order to evaluate the proposed method, it was compared with the other methods on different data sets (CELEB-DF (V2) data set, Face Forensics++ data set, and wild deep fake). The result shows that the proposed system achieved better results than the approaches in the literature.

show abstract

Section: Methodsmentioning

confidence: 99%

A Deep Fake Detection System Using Diffusion Model Based on Graph Based Image Segmentation

Al-Din,

Jaber,

Mahan

2023

Machine Learning and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Deepfake combines a deep understanding and artificial creation with political abuse, distribution of misleading information, and pornography. Thus, Ram et al (2023) analysed aspects of computer vision to determine the trustworthiness of digital content. Their method used fuzzy clustering to extract computer vision features.…”

Section: Ai-based Academic Integritymentioning

confidence: 99%

Unveiling the Potential: Experts' Perspectives on Artificial Intelligence Integration in Higher Education

Slimi,

Villarejo-Carballido

2024

EUROPEAN J ED RES

View full text Add to dashboard Cite

<p style="text-align:justify">This article investigates artificial intelligence (AI) implementation in higher education (HE) from experts' perspectives. It emphasises the view of AI's involvement in administrative activities in higher education, experts' opinions concerning the influence of the incorporation of AI on learning and teaching, and experts' views on applying AI specifically to assessment, academic integrity, and ethical considerations. The study used a qualitative method based on an unstructured qualitative interview with open-ended questions. The participants were thirteen individuals currently involved with higher education institutions and had various talents related to AI and education. Findings stress that implementing AI technology in administrative roles within higher education institutions is essential since it cuts costs, addresses problems efficiently and effectively, and saves time. The findings also revealed that AI plays a vital role in learning and teaching by speeding up the learning process, engaging learners and tutors, and personalising learning depending on the learner's needs within an entirely intelligent environment. AI can produce an accurate, objective, and suitable level of assessment. AI aids students in developing a stronger sense of integrity in their academic work by guiding them through AI-powered applications. AI must adhere to ethical laws and policies, ensuring its potential negative aspects are not overlooked or left unchecked.</p>

show abstract

“…Dolhansky, Brian and Howes, Russ and Pflaum, Ben and Baram, Nicole and Ferrer, Cristian [4] introduced a preview of the DFDC dataset that will be made available later this year with the goal of encouraging researchers to familiarise themselves with the data, providing preliminary findings, and comparing those findings to suggested baselines. R. Saravana Ram, M. Vinoth Kumar, Tareq M. Al-shami, Mehedi Masud, Hanan Aljuaid and Mohamed Abouhawwash in [5] suggested extracting features from the input deepfake image using fuzzy clustering. Kandasamy V, Hubálovsk, and Trojovsk [14] revealed the Deep learning approach with two levels for detecting deepfake photos and videos.…”

Section: Literature Surveymentioning

confidence: 99%

“…Figure: 2. Preprocessing System for Deepfake [5] Deepfake detection can consist of several components and techniques working together. By looking at the given figure 2, A high-level description of a hypothetical system is given below: Preprocessing: The system starts by preprocessing the input data, which could be a video, image, or audio file.…”

Section: Proposed Systemmentioning

confidence: 99%

See 1 more Smart Citation

Combining Computer Vision Techniques and Intraframe Noise Methods to Detect a Deepfake

Shelke,

Ranjan,

Kharade

et al. 2023

Data Science and Intelligent Computing Techniques

View full text Add to dashboard Cite

Deep fakes are synthetic videos created by deep learning algorithms that can convincingly depict individuals saying or doing things they never did. With the proliferation of deepfake videos in social media and the potential for them to cause significant harm, deep fake detection has become a pressing issue. In this study, we offer a unique method for detecting deepfakes by combining computer vision methods with intraframe noise. The proposed approach involves extracting features from the video frames, including texture, color, and edges, and then adding a layer of intraframe noise to the video frames. We tested the proposed method on a variety of benchmark datasets and found that it achieved high accuracy in detecting deepfake videos.

show abstract

Deep Fake Detection Using Computer Vision-Based Deep Neural Network with Pairwise Learning

Cited by 9 publications

References 43 publications

A Deep Fake Detection System Using Diffusion Model Based on Graph Based Image Segmentation

A Deep Fake Detection System Using Diffusion Model Based on Graph Based Image Segmentation

Unveiling the Potential: Experts' Perspectives on Artificial Intelligence Integration in Higher Education

Combining Computer Vision Techniques and Intraframe Noise Methods to Detect a Deepfake

Contact Info

Product

Resources

About