DeepFake Video Analysis using SIFT Features

Đorđević, Miljan; Milivojević, Milan S.; Gavrovska, Ana

doi:10.1109/telfor48224.2019.8971206

Cited by 7 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Guera & Delp (2019) used a recurrent neural network to detect deepfakes, this gives 96.7% of accuracy in detecting deepfakes. In the same way, Dordevic, Milivojevic & Gavrovska (2019) has used SIFT features, i.e ., brightness changes, scaling, etc ., to detect deepfakes. This gives 97.91% accuracy in detecting deepfakes DeepFaceLab.…”

Section: Discussionmentioning

confidence: 99%

“…The Scale Invariant Feature Transform (SIFT) algorithm ( Dordevic, Milivojevic & Gavrovska, 2019 ) and eyebrow matching ( Nguyen & Derakhshani, 2020 ) are also used in deepfake detection to calculate a match error. Nirkin et al (2021) used the Dual Short Face Detector (DSFD) ( Li et al, 2019 ) method to first capture the segmentation of the face in the video.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deepfake attack prevention using steganography GANs

Noreen¹,

Muneer²,

Gillani³

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Background Deepfakes are fake images or videos generated by deep learning algorithms. Ongoing progress in deep learning techniques like auto-encoders and generative adversarial networks (GANs) is approaching a level that makes deepfake detection ideally impossible. A deepfake is created by swapping videos, images, or audio with the target, consequently raising digital media threats over the internet. Much work has been done to detect deepfake videos through feature detection using a convolutional neural network (CNN), recurrent neural network (RNN), and spatiotemporal CNN. However, these techniques are not effective in the future due to continuous improvements in GANs. Style GANs can create fake videos with high accuracy that cannot be easily detected. Hence, deepfake prevention is the need of the hour rather than just mere detection. Methods Recently, blockchain-based ownership methods, image tags, and watermarks in video frames have been used to prevent deepfake. However, this process is not fully functional. An image frame could be faked by copying watermarks and reusing them to create a deepfake. In this research, an enhanced modified version of the steganography technique RivaGAN is used to address the issue. The proposed approach encodes watermarks into features of the video frames by training an “attention model” with the ReLU activation function to achieve a fast learning rate. Results The proposed attention-generating approach has been validated with multiple activation functions and learning rates. It achieved 99.7% accuracy in embedding watermarks into the frames of the video. After generating the attention model, the generative adversarial network has trained using DeepFaceLab 2.0 and has tested the prevention of deepfake attacks using watermark embedded videos comprising 8,074 frames from different benchmark datasets. The proposed approach has acquired a 100% success rate in preventing deepfake attacks. Our code is available at https://github.com/shahidmuneer/deepfakes-watermarking-technique.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Deepfake attack prevention using steganography GANs

Noreen¹,

Muneer²,

Gillani³

2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…These methods are typically deep (e.g., CNNs with multiple hidden layers to extract finer features) or shallow classifiers (e.g., Support Vector Machine (SVM) and neural networks with one layer). Some of the recent works include the use of capsule networks, where latent features are extracted using the VGG-19 network and fed into a network of 3 capsules (dynamic routing between capsules algorithm is employed to boost detection performance) [Nguyen et al 2019]; the use of optical flow fields to identify inter-frame dissimilarities/correlations and be used by CNN classifiers [Amerini et al 2019]; the extraction of biological signals hidden in videos, FakeCatcher [Ciftci and Demir 2019]; the use of the Scale-Invariant Feature Transform (SIFT) algorithm to analyze successive frames and differentiate between real and fake videos [Dordevic et al 2019]; and the detection of the lack of eye blinking in videos to exposed synthesized videos [Li et al 2018].…”

Section: Automatic Detectionmentioning

confidence: 99%

Towards a New Science of Disinformation

Pinhanez¹,

Flores²,

Vasconcelos³

et al. 2022

Preprint

View full text Add to dashboard Cite

How can we best address the dangerous impact that deep learninggenerated fake audios, photographs, and videos (a.k.a. deepfakes) may have in personal and societal life? We foresee that the availability of cheap deepfake technology will create a second wave of disinformation where people will receive specific, personalized disinformation through different channels, making the current approaches to fight disinformation obsolete. We argue that fake media has to be seen as an upcoming cybersecurity problem, and we have to shift from combating its spread to a prevention and cure framework where users have available ways to verify, challenge, and argue against the veracity of each piece of media they are exposed to. To create the technologies behind this framework, we propose that a new Science of Disinformation is needed, one which creates a theoretical framework both for the processes of communication and consumption of false content. Key scientific and technological challenges facing this research agenda are listed and discussed in the light of state-of-art technologies for fake media generation and detection, argument finding and construction, and how to effectively engage users in the prevention and cure processes.

show abstract

“…Furthermore, Yu et al [53] investigated the potential of GAN fingerprinting analysis for DeepFake detection. Dordevic et al [54] presented a method based on scale-invariant feature transform for DeepFake detection. Kaur et al [55] presented a sequential temporal analysis to detect face-swapped video clips using convolutional long short-term memory.…”

Section: Related Workmentioning

confidence: 99%

ADD: Attention-Based DeepFake Detection Approach

Khormali

Yuan

2021

BDCC

View full text Add to dashboard Cite

Recent advancements of Generative Adversarial Networks (GANs) pose emerging yet serious privacy risks threatening digital media’s integrity and trustworthiness, specifically digital video, through synthesizing hyper-realistic images and videos, i.e., DeepFakes. The need for ascertaining the trustworthiness of digital media calls for automatic yet accurate DeepFake detection algorithms. This paper presents an attention-based DeepFake detection (ADD) method that exploits the fine-grained and spatial locality attributes of artificially synthesized videos for enhanced detection. ADD framework is composed of two main components including face close-up and face shut-off data augmentation methods and is applicable to any classifier based on convolutional neural network architecture. ADD first locates potentially manipulated areas of the input image to extract representative features. Second, the detection model is forced to pay more attention to these forgery regions in the decision-making process through a particular focus on interpreting the sample in the learning phase. ADD’s performance is evaluated against two challenging datasets of DeepFake forensics, i.e., Celeb-DF (V2) and WildDeepFake. We demonstrated the generalization of ADD by evaluating four popular classifiers, namely VGGNet, ResNet, Xception, and MobileNet. The obtained results demonstrate that ADD can boost the detection performance of all four baseline classifiers significantly on both benchmark datasets. Particularly, ADD with ResNet backbone detects DeepFakes with more than 98.3% on Celeb-DF (V2), outperforming state-of-the-art DeepFake detection methods.

show abstract

DeepFake Video Analysis using SIFT Features

Cited by 7 publications

References 4 publications

Deepfake attack prevention using steganography GANs

Deepfake attack prevention using steganography GANs

Towards a New Science of Disinformation

ADD: Attention-Based DeepFake Detection Approach

Contact Info

Product

Resources

About