A Novel Neural Model based Framework for Detection of GAN Generated Fake Images

Agarwal, Samaksh; Girdhar, Nancy; Raghav, Himanshu

doi:10.1109/confluence51648.2021.9377150

Cited by 19 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the KF with label A has a predicted value that was closer to an unlabeled object in the new image than that of the KF with the label B, the new object would be labelled A. Once labelled, the KF will be updated with the labelled object's new measured position, using the update equations (8,9). If more objects are detected in later images than there are KF models, the labelling process will occur, and all unlabeled objects will be assigned a new KF model, initialized using its corresponding objects position.…”

Section: Kalman Filter (Kf) Methodsmentioning

confidence: 99%

“…These components are the Generator, whose purpose is to generate proper data, and the Discriminator, whose purpose is to detect flaws in the data that the Generator provides. This process stops when the Discriminator cannot distinguish differences between the generated and actual data any longer [9]. This concept can be used in a plethora of fields, with the most prominent being creating [10] and manipulating [11] images.…”

Section: Relevant Machine Learning Modelsmentioning

confidence: 99%

“…The minimum distance method, used in each of the filtering tracking methods, is then used to label the closest object. Once labelled, the KF will be updated with the labelled objects new measured position, using the update equations (8,9). After labelling the found object following the time-gap, the hybrid KF-SIF model will determine if the object is significantly far away from its previous location.…”

Section: Proposed Hybrid Kf-sif Solutionmentioning

confidence: 99%

See 2 more Smart Citations

Facial feature tracking method using a hybrid model of the Kalman filter and the sliding innovation filter

Wilkinson

Hilal²,

Gadsden

et al. 2023

Real-Time Image Processing and Deep Learning 2023

View full text Add to dashboard Cite

The purpose of this paper is to aid in detecting synthesized video (specifically created through the use of DeepFake) by exploring facial-feature tracking methods. Analyzing individual facial features, should allow for more successful detection of DeepFake videos according to H. Nguyen et al.'s research [22] and A. A. Maksutov's list of commonly use techniques to identify fabricated media [17]. To detect these facial features in images, Computer Vision techniques such as YOLOv3[24] can be used. Once detected, object-tracking methods should be explored. This paper will compare the accuracy of three existing object-tracking methods: the minimum-distance approach, the Kalman Filter (KF) method, and the Sliding Innovation Filter (SIF) method. Following this comparison, the paper proposes a novel hybrid object-tracking approach, in which the benefits of the KF method and SIF method are combined to provide a time-gap tolerant object-tracking method. Each of the models are tested on their ability to track multiple objects that follow different trajectories and compared against one another to identify the most effective manner of tracking.

show abstract

Section: Kalman Filter (Kf) Methodsmentioning

confidence: 99%

Section: Relevant Machine Learning Modelsmentioning

confidence: 99%

Section: Proposed Hybrid Kf-sif Solutionmentioning

confidence: 99%

See 1 more Smart Citation

Facial feature tracking method using a hybrid model of the Kalman filter and the sliding innovation filter

Wilkinson

Hilal²,

Gadsden

et al. 2023

Real-Time Image Processing and Deep Learning 2023

View full text Add to dashboard Cite

show abstract

“…GANs have also been proposed as means of analyzing spatiotemporal relationships of videos. An information theory-based approach was used to study the statistical distribution of fake and real frames, and the differential between them was used to make a decision [75].…”

Section: Adversarial Training-based Detectionmentioning

confidence: 99%

Evolution of Attacks on Intelligent Surveillance Systems and Effective Detection Techniques

Nagothu¹,

Poredi²,

Chen³

2023

Intelligent Video Surveillance - New Perspectives

View full text Add to dashboard Cite

Intelligent surveillance systems play an essential role in modern smart cities to enable situational awareness. As part of the critical infrastructure, surveillance systems are often targeted by attackers aiming to compromise the security and safety of smart cities. Manipulating the audio or video channels could create a false perception of captured events and bypass detection. This chapter presents an overview of the attack vectors designed to compromise intelligent surveillance systems and discusses existing detection techniques. With advanced machine learning (ML) models and computing resources, both attack vectors and detection techniques have evolved to use ML-based techniques more effectively, resulting in non-equilibrium dynamics. The current detection techniques vary from training a neural network to detect forgery artifacts to use the intrinsic and extrinsic environmental fingerprints for any manipulations. Therefore, studying the effectiveness of different detection techniques and their reliability against the defined attack vectors is a priority to secure the system and create a plan of action against potential threats.

show abstract

“…More recently, Agarwal et al [33] introduced a neural model for detecting fake images generated using GANs, working on a combination of images' frequency spectrum and Capsule Networks.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Review of Deep Learning-based Approaches for Deepfake Content Detection

Passos¹,

Jodas²,

Costa³

et al. 2022

Preprint

View full text Add to dashboard Cite

The fast-spreading information over the internet is essential to support the rapid supply of numerous public utility services and entertainment to users. Social networks and online media paved the way for modern, timely-communicationfashion and convenient access to all types of information. However, it also provides new chances for ill use of the massive amount of available data, such as spreading fake content to manipulate public opinion. Detection of counterfeit content has raised attention in the last few years for the advances in deepfake generation. The rapid growth of machine learning techniques, particularly deep learning, can predict fake content in several application domains, including fake image and video manipulation. This paper presents a comprehensive review of recent studies for deepfake content detection using deep learning-based approaches. We aim to broaden the state-of-the-art research by systematically reviewing the different categories of fake content detection. Furthermore, we report the advantages and drawbacks of the examined works and future directions towards the issues and shortcomings still unsolved on deepfake detection.

show abstract

A Novel Neural Model based Framework for Detection of GAN Generated Fake Images

Cited by 19 publications

References 10 publications

Facial feature tracking method using a hybrid model of the Kalman filter and the sliding innovation filter

Facial feature tracking method using a hybrid model of the Kalman filter and the sliding innovation filter

Evolution of Attacks on Intelligent Surveillance Systems and Effective Detection Techniques

A Review of Deep Learning-based Approaches for Deepfake Content Detection

Contact Info

Product

Resources

About