Deepfake Media Forensics: State of the Art and Challenges Ahead

arXiv 2408.00388 ↗First posted 1 Aug 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and Diffusion Models (DMs) are the main frameworks used to create Deepfakes, producing highly realistic yet fabricated content. While these technologies open up new creative possibilities, they also bring substantial ethical and security risks due to their potential misuse. The rise of such advanced media has led to the development of a cognitive bias known as Impostor Bias, where individuals doubt the authenticity of multimedia due to the awareness of AI's capabilities. As a result, Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques, especially Convolutional Neural Networks (CNNs). Research in forensic Deepfake technology encompasses five main areas: detection, attribution and recognition, passive authentication, detection in realistic scenarios, and active authentication. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 45 of its 88 references that are in the map. First posted on arXiv 1 Aug 2024.

Builds on

45 of 88 references.

References · 45

2015Deep Residual Learning for Image Recognitioncited by 51,809
2020Denoising Diffusion Probabilistic Modelscited by 20,851
2014Explaining and Harnessing Adversarial Examplescited by 7,287
2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
2013Intriguing properties of neural networkscited by 5,114
2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
2020Training Generative Adversarial Networks with Limited Datacited by 1,184
2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
2016Practical Black-Box Attacks against Machine Learningcited by 893
2018Robustness May Be at Odds with Accuracycited by 873
2019CNN-generated images are surprisingly easy to spot... for nowcited by 842

33 more

2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
2020What makes fake images detectable? Understanding properties that generalizecited by 272
2020Media Forensics and DeepFakes: an overviewcited by 208
2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 151
2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
2020DeepFake Detection by Analyzing Convolutional Tracescited by 81
2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
2021Fighting deepfakes by detecting GAN DCT anomaliescited by 39
2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 39
2021Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectorscited by 32
2020Fighting Deepfake by Exposing the Convolutional Traces on Imagescited by 24
2022MINTIME: Multi-Identity Size-Invariant Video Deepfake Detectioncited by 23
2023Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Modelscited by 20
2021Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motioncited by 15
2022On the Exploitation of Deepfake Model Recognitioncited by 14
2018On the Transferability of Adversarial Examples Against CNN-Based Image Forensicscited by 12
2020Preliminary Forensics Analysis of DeepFake Imagescited by 12
2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
2023GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusionscited by 10
2023Deepfake detection by exploiting surface anomalies: the SurFake approachcited by 9
2024On the Exploitation of DCT-Traces in the Generative-AI Domaincited by 9
20233D Face Reconstruction: the Road to Forensicscited by 7
2022Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detectioncited by 6
2023Not with my name! Inferring artists' names of input strings employed by Diffusion Modelscited by 6
2024DeepFeatureX Net: Deep Features eXtractors based Network for discriminating synthetic from real imagescited by 6
2024Continuous fake media detection: adapting deepfake detectors to new generative techniquescited by 6
2022Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation of Predictive Modelscited by 5
2020Identifying Invariant Texture Violation for Robust Deepfake Detectioncited by 4
2018ABE-Cities: An Attribute-Based Encryption System for Smart Citiescited by 1
2023A One-Class Classifier for the Detection of GAN Manipulated Multi-Spectral Satellite Imagescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

Similar, not cited

Close in wording, no citation either way