Pith. sign in

REVIEW 7 cited by

Aligned Datasets Improve Detection of Latent Diffusion-Generated Images

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.11835 v3 pith:OYH3WYCJ submitted 2024-10-15 cs.CV

Anirudh Sundara Rajan , Utkarsh Ojha , Jedidiah Schloesser , Yong Jae Lee This is my paper
classification cs.CV
keywords imagesfakerealdetectorimagealignedldmsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic content, resolution, file format, etc. Fake image detectors are usually built in a data driven way, where a model is trained to separate real from fake images. Existing works primarily investigate network architecture choices and training recipes. In this work, we argue that in addition to these algorithmic choices, we also require a well aligned dataset of real/fake images to train a robust detector. For the family of LDMs, we propose a very simple way to achieve this: we reconstruct all the real images using the LDMs autoencoder, without any denoising operation. We then train a model to separate these real images from their reconstructions. The fakes created this way are extremely similar to the real ones in almost every aspect (e.g., size, aspect ratio, semantic content), which forces the model to look for the LDM decoders artifacts. We empirically show that this way of creating aligned real/fake datasets, which also sidesteps the computationally expensive denoising process, helps in building a detector that focuses less on spurious correlations, something that a very popular existing method is susceptible to. Finally, to demonstrate just how effective the alignment in a dataset can be, we build a detector using images that are not natural objects, and present promising results. Overall, our work identifies the subtle but significant issues that arise when training a fake image detector and proposes a simple and inexpensive solution to address these problems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Test-Time Curriculum for Open-Set AIGC Detection

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A curriculum-based test-time adaptation method, using balanced confident pseudo-labels and multi-scale refinement, improves AIGC detector accuracy on unseen generators by 11 to 29 points over its starting detector.

  2. GlobalForge: Towards Robust AI-Generated Image Detection

    cs.CV 2026-07 conditional novelty 6.0 of 10

    GlobalForge improves AI-generated image detection under real-world degradation by suppressing local shortcuts and enforcing long-range structural reasoning, outperforming prior state-of-the-art by 5.89% average balanc...

  3. HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.

  4. Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

    cs.CV 2026-05 conditional novelty 6.0 of 10

    SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.

  5. Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.

  6. Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    FGINet uses a band-masked frequency encoder and layer-wise gated injection to fuse frequency artifacts with vision foundation model semantics, plus hyperspherical compactness learning, to achieve better generalization...

  7. HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    HEDGE is a heterogeneous ensemble using progressive DINOv3 training, multi-scale features, and MetaCLIP2 diversity with dual-gating fusion to achieve robust AI-generated image detection and 4th place in the NTIRE 2026...

Pith tools