Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking

Demir, İlke; Ciftci, Umur Aybars

doi:10.1145/3448017.3457387

Cited by 30 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tais achados, tanto da análise da base de dados do Celeb-DF como do Face-forencis++, concordam com os trabalhos recentes de [Nguyen and Derakhshani 2020, Tolosana et al 2021, Demir and Ciftci 2021, Gerstner and Farid 2022 na identificac ¸ão das regiões que auxiliam na detecc ¸ão de uma deepfake.…”

Section: Análise Das Bases De Dados (Estatística E Eye-tracking)unclassified

“…Neste contexto, a literatura afim aponta distintas técnicas para identificar uma deepfake, porém resultam da observac ¸ão das técnicas citadas anteriormente de forma isolada [Chen et al 2020, Demir andCiftci 2021] ou combinada de duas ou mais técnicas [Tariq et al 2021], seja analisando somente a face [Tolosana et al 2021] ou combinando análise das emoc ¸ões com áudio [Mittal et al 2020]. Em se tratando de um tema recente, ainda não há um consenso tanto para categorizar os métodos de detecc ¸ão de deepfakes, como para identificar os tipos de deepfakes.…”

Section: Introduc ¸ãOunclassified

“…Expressões faciais) e ambientais (ex. Iluminac ¸ão), para analisar quais são as regiões que identificam uma deepfake em quadros de vídeos de faces frontais [Tolosana et al 2021, Demir and Ciftci 2021, Gerstner and Farid 2022.…”

Section: Introduc ¸ãOunclassified

See 2 more Smart Citations

Sobel filter and linear classification for deepfake analysis of faces

Tamanaka,

Thomaz

2023

Anais Do XX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2023)

View full text Add to dashboard Cite

Through artificial intelligence (AI) techniques, deepfakes (deep learning + fakes) are created. Currently, almost six years after this topic's popularization, some people have been using AI algorithms to change, for example, face. In this scenario, this article proposes to identify the most discriminating characteristics, based on the multivariate statistical learning techniques, with and without the Sobel filter. Complementarily, we aim to analyze the areas that humans have visually identified as relevant to detect a deepfake. The results show that the statistical model (PCA plus MLDA) combined with the Sobel filter correctly classified most of the images, highlighting the regions that discriminate a deepfake.

show abstract

Section: Análise Das Bases De Dados (Estatística E Eye-tracking)unclassified

Section: Introduc ¸ãOunclassified

See 1 more Smart Citation

Sobel filter and linear classification for deepfake analysis of faces

Tamanaka,

Thomaz

2023

Anais Do XX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2023)

View full text Add to dashboard Cite

show abstract

“…The authors of [89] discussed several biological signals for deepfake video detection, eye and gaze properties, by which deepfakes differ. Furthermore, the researchers combined those characteristics into signatures and compared original and fake videos, generating geometric, visual, metric, temporal, and spectral variances.…”

Section: Deepfake Video Detection Using Biological Signalsmentioning

confidence: 99%

A Review of Image Processing Techniques for Deepfakes

Shahzad

Rustam

Flores

et al. 2022

Sensors

View full text Add to dashboard Cite

Deep learning is used to address a wide range of challenging issues including large data analysis, image processing, object detection, and autonomous control. In the same way, deep learning techniques are also used to develop software and techniques that pose a danger to privacy, democracy, and national security. Fake content in the form of images and videos using digital manipulation with artificial intelligence (AI) approaches has become widespread during the past few years. Deepfakes, in the form of audio, images, and videos, have become a major concern during the past few years. Complemented by artificial intelligence, deepfakes swap the face of one person with the other and generate hyper-realistic videos. Accompanying the speed of social media, deepfakes can immediately reach millions of people and can be very dangerous to make fake news, hoaxes, and fraud. Besides the well-known movie stars, politicians have been victims of deepfakes in the past, especially US presidents Barak Obama and Donald Trump, however, the public at large can be the target of deepfakes. To overcome the challenge of deepfake identification and mitigate its impact, large efforts have been carried out to devise novel methods to detect face manipulation. This study also discusses how to counter the threats from deepfake technology and alleviate its impact. The outcomes recommend that despite a serious threat to society, business, and political institutions, they can be combated through appropriate policies, regulation, individual actions, training, and education. In addition, the evolution of technology is desired for deepfake identification, content authentication, and deepfake prevention. Different studies have performed deepfake detection using machine learning and deep learning techniques such as support vector machine, random forest, multilayer perceptron, k-nearest neighbors, convolutional neural networks with and without long short-term memory, and other similar models. This study aims to highlight the recent research in deepfake images and video detection, such as deepfake creation, various detection algorithms on self-made datasets, and existing benchmark datasets.

show abstract

“…Behavioural artifacts involve inconsistencies in physical attributes. The main features investigated are facial attributes [16], head pose [17], facial expression [18], emotions [19,20], gaze tracking [21,22], and blink detection [23].…”

Section: Introductionmentioning

confidence: 99%

DeepFakes Have No Heart: A Simple rPPG-Based Method to Reveal Fake Videos

Boccignone,

Bursic,

Cuculo

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We present a simple, yet general method to detect fake videos displaying human subjects, generated via Deep Learning techniques. The method relies on gauging the complexity of heart rate dynamics as derived from the facial video streams through remote photoplethysmography (rPPG). Features analyzed have a clear semantics as to such physiological behaviour. The approach is thus explainable both in terms of the underlying context model and the entailed computational steps. Most important, when compared to more complex state-of-the-art detection methods, results so far achieved give evidence of its capability to cope with datasets produced by different deep fake models.

show abstract

Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking

Cited by 30 publications

References 54 publications

Sobel filter and linear classification for deepfake analysis of faces

Sobel filter and linear classification for deepfake analysis of faces

A Review of Image Processing Techniques for Deepfakes

DeepFakes Have No Heart: A Simple rPPG-Based Method to Reveal Fake Videos

Contact Info

Product

Resources

About