An Experimental Evaluation on Deepfake Detection using Deep Face Recognition

Ramachandran, Sreeraj; Nadimpalli, Aakash Varma; Rattani, Ajita

doi:10.1109/iccst49569.2021.9717407

Cited by 26 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generating face synthesis images or videos required only editing skills and a lot of time to implement this tool in the swapping of face images or videos like deepfakes [26]. The significant techniques of deep learning have got in the various applications of computer vision.…”

Section: Review Of Literaturementioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph

Arunkumar

Sangeetha

Raja³

et al. 2022

ITC

View full text Add to dashboard Cite

In digital manipulation, creating fake images/videos or swapping face images/videos with another person is done by using a deep learning algorithm is termed deep fake. Fake pornography is a harmful one because of the inclusion of fake content in the hoaxes, fake news, and fraud things in the financial. The Deep Learning technique is an effective tool in the detection of deep fake images or videos. With the advancement of Generative adversarial networks (GAN) in the deep learning techniques, deep fake has become an essential one in the social media platform. This may threaten the public, therefore detection of deep fake images/videos is needed. For detecting the forged images/videos, many research works have been done and those methods are inefficient in the detection of new threats or newly created forgery images or videos, and also consumption time is high. Therefore, this paper focused on the detection of different types of fake images or videos using Fuzzy Fisher face with Capsule dual graph (FFF-CDG). The data set used in this work is FFHQ, 100K-Faces DFFD, VGG-Face2, and Wild Deep fake. The accuracy for FFHQ datasets, the existing and proposed systems obtained the accuracy of 81.5%, 89.32%, 91.35%, and 95.82% respectively.

show abstract

Section: Review Of Literaturementioning

confidence: 99%

“…One is the Two-Stage method, built on R-CNN [6,17,5] and TridenNet [32], among other algorithms. The next is the SSD [24,26,16] and YOLO-based One-Stage method, which has excellent actual improvement in multi-scale object recognition.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph

Arunkumar

Sangeetha

Raja³

et al. 2022

ITC

View full text Add to dashboard Cite

show abstract

“…In this section, we will discuss the existing countermeasure proposed for deep fake detection. Most of the existing methods are CNN-based classification baselines trained for deep fake detection [15,10,25,27].…”

Section: Deepfake Detectionmentioning

confidence: 99%

“…Apart from the aforementioned CNN-based deep fake detection methods, spatial temporal information using Long Short-term Memory (LSTM) networks [6], facial and behavioral biometrics (i.e., facial expression, head, and body movement), and lipforensics [14] have been used for deep fake detection [13,2,3,27]. In [14], LipForensics that targets high-level semantic irregularities in mouth movements common in many generated deepfake videos, is used for deepfake detection.…”

Section: Deepfake Detectionmentioning

confidence: 99%

GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection

Nadimpalli¹,

Rattani²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Facial forgery by deepfakes has raised severe societal concerns. Several solutions have been proposed by the vision community to effectively combat the misinformation on the internet via automated deepfake detection systems. Recent studies have demonstrated that facial analysis-based deep learning models can discriminate based on protected attributes. For the commercial adoption and massive roll-out of the deepfake detection technology, it is vital to evaluate and understand the fairness (the absence of any prejudice or favoritism) of deepfake detectors across demographic variations such as gender and race. As the performance differential of deepfake detectors between demographic subgroups would impact millions of people of the deprived sub-group. This paper aims to evaluate the fairness of the deepfake detectors across males and females. However, existing deepfake datasets are not annotated with demographic labels to facilitate fairness analysis. To this aim, we manually annotated existing popular deepfake datasets with gender labels and evaluated the performance differential of current deepfake detectors across gender. Our analysis on the gender-labeled version of the datasets suggests (a) current deepfake datasets have skewed distribution across gender, and (b) commonly adopted deepfake detectors obtain unequal performance across gender with mostly males outperforming females. Finally, we contributed a gender-balanced and annotated deepfake dataset, GBDF, to mitigate the performance differential and to promote research and development towards fairness-aware deep fake detectors. The GBDF dataset is publicly available at: https://github.com/aakash4305/GBDF

show abstract

“…While the previous general face forgery detection also applies to such scenarios, they rarely utilize the available real portraits of the identities of concern, which we show helpful in solving the challenges. There have been a few works [17], [23], [24], [25] that make use of reference real images or videos to improve generalization. However, these approaches only leverage one specific reference and for inference only, making the detection accuracy sensitive to the choice of the reference.…”

Section: Introductionmentioning

confidence: 99%

Watch Out for the Confusing Faces: Detecting Face Swapping with the Probability Distribution of Face Identification Models

Duan¹,

Zhang²,

Yu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, face swapping has been developing rapidly and achieved a surprising reality, raising concerns about fake content. As a countermeasure, various detection approaches have been proposed and achieved promising performance. However, most existing detectors struggle to maintain performance on unseen face swapping methods and low-quality images. Apart from the generalization problem, current detection approaches have been shown vulnerable to evasion attacks crafted by detection-aware manipulators. Lack of robustness under adversary scenarios leaves threats for applying face swapping detection in real world. In this paper, we propose a novel face swapping detection approach based on face identification probability distributions, coined as IdP FSD, to improve the generalization and robustness. IdP FSD is specially designed for detecting swapped faces whose identities belong to a finite set, which is meaningful in real-world applications. Compared with previous general detection methods, we make use of the available real faces with concerned identities and require no fake samples for training. IdP FSD exploits face swapping's common nature that the identity of swapped face combines that of two faces involved in swapping. We reflect this nature with the confusion of a face identification model and measure the confusion with the maximum value of the output probability distribution. What's more, to defend our detector under adversary scenarios, an attention-based finetuning scheme is proposed for the face identification models used in IdP FSD. Extensive experiments show that the proposed IdP FSD not only achieves high detection performance on different benchmark datasets and image qualities but also raises the bar for manipulators to evade the detection.

show abstract

An Experimental Evaluation on Deepfake Detection using Deep Face Recognition

Cited by 26 publications

References 19 publications

Deep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph

Deep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph

GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection

Watch Out for the Confusing Faces: Detecting Face Swapping with the Probability Distribution of Face Identification Models

Contact Info

Product

Resources

About