• Corpus ID: 232075725

Countering Malicious DeepFakes: Survey, Battleground, and Horizon

  title={Countering Malicious DeepFakes: Survey, Battleground, and Horizon},
  author={Felix Juefei-Xu and Run Wang and Yihao Huang and Qing Guo and Lei Ma and Yang Liu},
The creation or manipulation of facial appearance through deep generative approaches, known as DeepFake, have achieved significant progress and promoted a wide range of benign and malicious applications, e.g., visual effect assistance in movie and misinformation generation by faking famous persons. The evil side of this new technique poses another popular study, i.e., DeepFake detection aiming to identify the fake faces from the real ones. With the rapid development of the DeepFake-related… 
DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learning
This study presents challenges, research trends, and directions related to DeepFake creation and detection techniques by reviewing the notable research in the DeepFake domain to facilitate the development of more robust approaches that could deal with the more advance DeepFake in future.
Towards Solving the DeepFake Problem : An Analysis on Improving DeepFake Detection using Dynamic Face Augmentation
A simple data augmentation method termed Face-Cutout is proposed, which dynamically cuts out regions of an image using the face landmark information and achieves a reduction in LogLoss on different datasets, compared to other occlusion-based techniques.
Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering
This paper proposes a simple yet powerful pipeline to reduce the artifact patterns of fake images without hurting image quality by performing implicit spatial-domain notch filtering, and names it DeepNotch.
ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks
This work proposes adversarial-aware spectrum analysis for vulnerable block localization that considers the neurons’ status and weights’ gradients in blocks during the forward and backward processes, which enables more accurate candidate block localization for repairing even under a few examples.
FakeLocator: Robust Localization of GAN-Based Face Manipulations via Semantic Segmentation Networks with Bells and Whistles
The proposed FakeLocator can obtain high localization accuracy, at full resolution, on manipulated facial images, and is robust against various real-world facial image degradations such as JPEG compression, low-resolution, noise, and blur.
DmyT: Dummy Triplet Loss for Deepfake Detection
This paper investigates the use of triplet loss with fixed positive and negative vectors as a replacement for semi-hard triplets but requires less computation, as the triplets are fixed, and doesn't rely on a linear classifier for prediction.
FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
This paper devise a deep learning-based approach, named FakeTagger, with a simple yet effective encoder and decoder design along with channel coding to embed message to the facial image, which is to recover the embedded message after various drastic GAN-based DeepFake transformation with high confidence.


WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop and test the effectiveness of deepfake detectors against real-world deepfakes, and proposes two (eg. 2D and 3D) Attention-based Deepfake Detection Networks (ADDNets) to leverage the attention masks on real/fake faces for improved detection.
DeepTag: Robust Image Tagging for DeepFake Provenance.
A deep learning-based approach with a simple yet effective encoder and decoder design to embed message to the facial image, which is to recover the embedded message after various drastic GAN-based DeepFake transformation with high confidence.
DeepFake Detection by Analyzing Convolutional Traces
This work focuses on the analysis of Deepfakes of human faces with the objective of creating a new detection method able to detect a forensics trace hidden in images: a sort of fingerprint left in the image generation process.
Adversarial Threats to DeepFake Detection: A Practical Perspective
This work studies the extent to which adversarial perturbations transfer across different models and proposes techniques to improve the transferability of adversarial examples, and creates more accessible attacks using Universal Adversarial Perturbations which pose a very feasible attack scenario since they can be easily shared amongst attackers.
OC-FakeDect: Classifying Deepfakes Using One-class Variational Autoencoder
  • Hasam Khalid, Simon S. Woo
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
OC-FakeDect is proposed, which uses a one-class Variational Autoencoder (VAE) to train only on real face images and detects non-real images such as deepfakes by treating them as anomalies.
Media Forensics and DeepFakes: An Overview
  • L. Verdoliva
  • Computer Science
    IEEE Journal of Selected Topics in Signal Processing
  • 2020
This review paper aims to present an analysis of the methods for visual media integrity verification, that is, the detection of manipulated images and videos, with special emphasis on the emerging phenomenon of deepfakes, fake media created through deep learning tools, and on modern data-driven forensic methods to fight them.
Swapped face detection using deep learning and subjective assessment
This study uses deep transfer learning for face swapping detection, showing true positive rates greater than 96% with very few false alarms and distinguished from existing methods that only provide detection accuracy, which is critical for trust in the deployment of such detection systems.
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
This paper presents the first publicly available set of Deepfake videos generated from videos of VidTIMIT database, and demonstrates that GAN-generated Deep fake videos are challenging for both face recognition systems and existing detection methods.
FakeRetouch: Evading DeepFakes Detection via the Guidance of Deliberate Noise
This work proposes a simple yet powerful framework to reduce the artifact patterns of fake images without hurting image quality and uses a combination of additive noise and deep image filtering to reconstruct the fake images, and it is hoped that the found vulnerabilities can help improve the future generation DeepFake detection methods.
Deep Learning for Deepfakes Creation and Detection
A survey of algorithms used to create deepfakes and, more importantly, methods proposed to detectDeepfake in the literature to date is presented and extensive discussions on challenges, research trends and directions related to deepfake technologies are presented.