Deepfake Media Forensics: Status and Future Challenges

Abstract

The rise of AI-generated synthetic media, or deepfakes, has introduced unprecedented opportunities and challenges across various fields, including entertainment, cybersecurity, and digital communication. Using advanced frameworks such as Generative Adversarial Networks (GANs) and Diffusion Models (DMs), deepfakes are capable of producing highly realistic yet fabricated content, while these advancements enable creative and innovative applications, they also pose severe ethical, social, and security risks due to their potential misuse. The proliferation of deepfakes has triggered phenomena like "Impostor Bias", a growing skepticism toward the authenticity of multimedia content, further complicating trust in digital interactions. This paper is mainly based on the description of a research project called FF4ALL (FF4ALL-Detection of Deep Fake Media and Life-Long Media Authentication) for the detection and authentication of deepfakes, focusing on areas such as forensic attribution, passive and active authentication, and detection in real-world scenarios. By exploring both the strengths and limitations of current methodologies, we highlight critical research gaps and propose directions for future advancements to ensure media integrity and trustworthiness in an era increasingly dominated by synthetic media.

Keywords: audio deepfake detection; deepfake attribution and recognition; deepfake authentication techniques; deepfake detection; media forensics.

Figure 1

Generic diagram of the deepfake creation process.

Figure 2

(a) The GAN framework consists of a Generator (G) that creates synthetic data $\overline{x}$ from random noise z, aiming to learn the data distribution $p_{data}$, and a Discriminator (D) that distinguishes between real and generated data. Both models are trained simultaneously in an adversarial manner; (b) The Diffusion Model [8] uses a fixed Markov chain to add Gaussian noise to data, approximating the posterior distribution $q\left(x_t\right|x_{t-1})\mathrm{for}t=1,\dots ,T$. The goal is to learn the reverse process $p_{\theta }\left(x_{t-1}\right|x_t)$ to generate data by reversing the noise-adding chain, where $x_1,\dots ,x_T$ are latent variables with the same dimensionality as $x_0$.

Figure 3

Taxonomy of Deepfake Detection Methods. Detection techniques are categorized into four primary groups: general network-based approaches, methods focusing on visual artifacts, approaches targeting biological inconsistencies, and techniques leveraging texture and spatio-temporal consistency. Each category addresses specific characteristics of manipulated content.

Figure 4

Example of deepfake detection features. The full face (a) exhibits visual artifacts, such as unnatural pixel formations around the facial features (e.g., glasses and skin edges). These are indicative of irregularities introduced by generative algorithms or compression distortions. The zoomed-in region (b) around the mouth shows potential texture inconsistencies, such as unnatural blending of lip textures and a lack of smooth transitions typical of natural skin and lip patterns.

Figure 5

A conceptual pipeline for deepfake detection and model recognition, illustrating the process of identifying whether an image is real or synthetic, determining the generative architecture, and tracing the specific model instance used for creation.

Figure 6

The TrueFace Dataset [158], comprising 80k fake images generated with StyleGAN models and 70k real images, of which 60k have been also shared on three distinct social networks.