Deepfakes represent one of the toughest challenges in the world of Cybersecurity and Digital Forensics, especially considering the high-quality results obtained with recent generative AI-based solutions. Almost all generative models leave unique traces in synthetic data that, if analyzed and identified in detail, can be exploited to improve the generalization limitations of existing deepfake detectors. In this paper we analyzed deepfake images in the frequency domain generated by both GAN and Diffusion Model engines, examining in detail the underlying statistical distribution of Discrete Cosine Transform (DCT) coefficients. Recognizing that not all coefficients contribute equally to image detection, we hypothesize the existence of a unique "discriminative fingerprint", embedded in specific combinations of coefficients. To identify them, Machine Learning classifiers were trained on various combinations of coefficients. In addition, the Explainable AI (XAI) LIME algorithm was used to search for intrinsic discriminative combinations of coefficients. Finally, we performed a robustness test to analyze the persistence of traces by applying JPEG compression. The experimental results reveal the existence of traces left by the generative models that are more discriminative and persistent at JPEG attacks.

翻译：深度伪造（Deepfakes）是网络安全与数字取证领域最严峻的挑战之一，尤其是考虑到近年来基于生成式AI解决方案所产生的高质量结果。几乎所有生成模型都会在合成数据中留下独特痕迹，若对这些痕迹进行详细分析与识别，便可利用其改进现有深度伪造检测器在泛化能力上的局限性。本文从频域角度分析了由生成对抗网络（GAN）和扩散模型（Diffusion Model）生成的深度伪造图像，并详细研究了离散余弦变换（DCT）系数的潜在统计分布特征。鉴于并非所有系数对图像检测的贡献相同，我们假设存在一个嵌入特定系数组合中的独特"判别性指纹"。为识别该指纹，我们基于多种系数组合训练了机器学习分类器。此外，采用可解释人工智能（XAI）领域的LIME算法搜索系数间内在的判别性组合。最后，通过应用JPEG压缩进行了鲁棒性测试，以分析痕迹的持久性。实验结果表明，生成模型遗留的痕迹在JPEG攻击下具有更强的判别性和持久性。