Deepfakes, synthetic images generated by deep learning algorithms, represent
one of the biggest challenges in the field of Digital Forensics. The scientific
community is working to develop approaches that can discriminate the origin of
digital images (real or AI-generated). However, these methodologies face the
challenge of generalization, that is, the ability to discern the nature of an
image even if it is generated by an architecture not seen during training. This
usually leads to a drop in performance. In this context, we propose a novel
approach based on three blocks called Base Models, each of which is responsible
for extracting the discriminative features of a specific image class (Diffusion
Model-generated, GAN-generated, or real) as it is trained by exploiting
deliberately unbalanced datasets. The features extracted from each block are
then concatenated and processed to discriminate the origin of the input image.
Experimental results showed that this approach not only demonstrates good
robust capabilities to JPEG compression but also outperforms state-of-the-art
methods in several generalization tests. Code, models and dataset are available
at this https URL

基于三个块的新型方法，通过提取具有分辨力的特征来区分不同类型的图像，进而解决深度学习算法生成的合成图像在数字取证领域中的挑战，实验证明该方法在 JPEG 压缩和泛化测试方面具有良好的鲁棒性并超越了现有方法。

DeepFeatureX Net: 基于深度特征提取网络的合成图像与真实图像区分

DeepFeatureX Net: Deep Features eXtractors based Network for  discriminating synthetic from real images

We propose a belief-formation model where agents attempt to discriminate
between two theories, and where the asymmetry in strength between confirming
and disconfirming evidence tilts beliefs in favor of theories that generate
strong (and possibly rare) confirming evidence and weak (and frequent)
disconfirming evidence. In our model, limitations on information processing
provide incentives to censor weak evidence, with the consequence that for some
discrimination problems, evidence may become mostly one-sided, independently of
the true underlying theory. Sophisticated agents who know the characteristics
of the censored data-generating process are not lured by this accumulation of
``evidence'', but less sophisticated ones end up with biased beliefs.

在我们的研究中，我们提出了一个信念形成模型，其中代理试图区分两种理论，证实和证伪证据之间的强度不对称性使得信念倾向于生成强（可能是罕见的）证实证据和弱（频繁的）证伪证据的理论。在我们的模型中，信息处理的限制导致代理倾向于审查弱证据，这导致在某些区分问题中，证据可能大部分是单面的，与真实的基本理论无关。了解被审查的数据生成过程特征的复杂代理不会被这些所谓的 “证据” 所迷惑，但是不太复杂的代理最终会形成有偏见的信念。