This work investigates what cues are exploited by foundation-model-based detectors to distinguish real images from diffusion-generated ones and suggests that foundation-model-based detectors succeed by capturing non-semantic low-to-mid frequency distributional discrepancies between real and diffusion-generated images.
Abstract
Vision foundation models have recently emerged as powerful feature extractors for detecting AI-generated images, achieving strong generalization across generators and robustness to common image degradations. However, the reason behind their effectiveness is poorly understood. In this work, we investigate what cues are exploited by foundation-model-based detectors to distinguish real images from diffusion-generated ones. To this end, we design an ad hoc analysis protocol based on DDIM inversion. Given a real image we generate a sequence of synthetic copies by changing the depth of DDIM inversion. Even though most copies are semantically identical to the real reference, the detector score varies significantly across them due to subtle traces introduced by the diffusion synthesis, showing that its decision is not primarily driven by semantic failures. Through a frequency-swapping analysis, we further reveal that the discriminative cues exploited by the detectors are mainly localized in the low-to-mid frequency range, rather than only in the high-frequency range, as is the case for artifacts commonly associated with generative models. Finally, a latent-space analysis shows that regenerated images exhibit reduced variance and effective dimensionality, indicating that diffusion models do not fully reproduce the variability of real data. Overall, our results suggest that foundation-model-based detectors succeed by capturing non-semantic low-to-mid frequency distributional discrepancies between real and diffusion-generated images. These findings provide new insight into the robustness and generalization of such detectors and suggest directions for more interpretable forensic methods.
RippleNet is proposed, an AI-generated image detection framework based on local differential signals that adaptively identifies forgery-sensitive regions and constructs multi-directional, multi-scale differential representations within local neighborhoods, explicitly characterizing anomalous patterns in neighborhood statistics.
Jiazhen Yang, Ruijin Jin, Junjun Zheng et al.· 0 citations
This work establishes a new paradigm for generated image detection by recasting the detection task as a problem of machine unlearning, and introduces two detection methods: data-free detection, which prunes model parameters to induce unlearning without data access, and data-driven detection, which optimizes LVMs to unlearn knowledge tied to generated images.
Jun Nie, Yonggang Zhang, Tongliang Liu et al.· 0 citations
DBINDS, a diffusion-model-inversion-based detection framework that extends the analysis from the pixel domain to a diffusion-inversion-derived latent-noise space, is proposed and a composite of spatiotemporal correlation and spatiotemporal texture features is identified as the Best Dual Combination.
Yanlin Wu, Xiaogang Yuan, Dezhi An· Journal of King Saud Univers...· 0 citations
AI-generated images have proliferated rapidly, motivating extensive research. Most existing AI-generated image detectors are developed and evaluated under image-free generation paradigms, such as noise-based or text-guided generation. However, image-conditioned generation has become increasingly important in practical applications, as it enables more fine-grained control over generated content. Detecting AI-generated images across these two paradigms creates a critical cross-paradigm detection problem that has long been overlooked. To study this problem, we construct ConImageGen, a benchmark for cross-paradigm AI-generated image detection. Evaluations on ConImageGen show that existing detectors fail to generalize reliably across image-free and image-conditioned generation. To address this failure, this paper identifies a cross-paradigm forensic cue and provides a new perspective for generalized AI-generated image detection. Specifically, by suppressing semantic interference, we visualize, for the first time, semantics-irrelevant texture patterns across generation paradigms. These patterns exhibit structured local-global texture relations, indicating a generalizable form of forensic evidence. Motivated by this finding, we shift the focus from directly exploiting explicit artifacts to modeling texture relations and propose DTS-Det, a detection framework that captures and leverages such relations for generalized AI-generated image detection. Extensive experiments validate the effectiveness of our method. DTS-Det achieves state-of-the-art performance across diverse evaluation settings, reaching 99.6% ACC on ConImageGen with a 10.5% gain over the best baseline. It also achieves 93.2%/94.1% ACC in cross-dataset evaluation on PicoBanana/RAID and maintains detection rates of 95.2%/88.1% under reconstruction attacks and black-box adversarial attacks, respectively.
Haoyu Wang, Yiming Qin, Zhongjie Ba et al.· 0 citations
This work formats the AI-generated image detection task as a Visual Question Answering problem, leveraging a fine-tuned vision-language framework to fully exploit the complementary information between visual and textual modalities, and proposes a novel high-resolution AI-generated image detector, termed LHSDet.
Qian Yao, Jun-Jie Huang, Yongjun Wang et al.· 0 citations
GFRE employs a lightweight autoencoder to model the reconstructability of image representations, producing a reconstruction signal that is inherently generator-agnostic and transferable across diverse generative processes, enabling efficient and scalable deployment.
Qinghui He, Haifeng Zhang, ∗. BoLiu et al.· 0 citations