Pith. sign in

REVIEW 15 cited by

A Single Simple Patch is All You Need for AI-generated Image Detection

Not yet reviewed by Pith; the record is open.

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 2402.01123 v2 pith:KRVHZEIQ submitted 2024-02-02 cs.CV

A Single Simple Patch is All You Need for AI-generated Image Detection

classification cs.CV
keywords imagesfakeperformancesimpleai-generateddetectiongeneratedgenerating
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The recent development of generative models unleashes the potential of generating hyper-realistic fake images. To prevent the malicious usage of fake images, AI-generated image detection aims to distinguish fake images from real images. However, existing method suffer from severe performance drop when detecting images generated by unseen generators. We find that generative models tend to focus on generating the patches with rich textures to make the images more realistic while neglecting the hidden noise caused by camera capture present in simple patches. In this paper, we propose to exploit the noise pattern of a single simple patch to identify fake images. Furthermore, due to the performance decline when handling low-quality generated images, we introduce an enhancement module and a perception module to remove the interfering information. Extensive experiments demonstrate that our method can achieve state-of-the-art performance on public benchmarks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

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

  1. ImageAttributionBench: How Far Are We from Generalizable Attribution?

    cs.CV 2026-05 unverdicted novelty 7.0

    ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.

  2. Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images

    cs.CV 2026-06 unverdicted novelty 6.0

    Color transformations expose statistical discrepancies in synthetic images, supporting a classifier with 93.27% average accuracy and robustness to post-processing.

  3. OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction

    cs.LG 2026-04 conditional novelty 6.0

    An ICU risk model pretrained with ICD-ontology-aware contrastive learning and fine-tuned by distilling clinical notes achieves the best vitals-only results on MIMIC tasks.

  4. Detecting Diffusion-generated Images via Dynamic Assembly Forests

    cs.CV 2026-04 unverdicted novelty 6.0

    DAF is a novel deep forest-based detector for diffusion-generated images that uses fewer parameters and less computation than DNN methods while matching their performance.

  5. Retrieval-Driven Training-Free AI-Generated Video Attribution

    cs.CV 2026-07 conditional novelty 5.0

    A training-free retrieval pipeline using adaptive color transforms, multi-scale quantized residuals, and temporal aggregation attributes AI-generated videos to one of eight generators with 84.6% Rank-1 and 78.3% mAP o...

  6. MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localization

    cs.CV 2026-05 unverdicted novelty 5.0

    MFVLR uses multi-domain vision-language reconstruction with a fine-grained language transformer, multi-domain vision encoder, and vision injection module to achieve generalizable detection and localization of diffusio...

  7. OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction

    cs.LG 2026-04 unverdicted novelty 5.0

    OC-Distill combines ontology-aware contrastive pretraining with cross-modal distillation to improve ICU risk prediction performance and label efficiency while using only vital signs at inference.

  8. RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images

    cs.CV 2026-07 conditional novelty 4.0

    Reversing bit-plane weights ('bit-reversed image') plus a gradient-selected 32×32 patch lets a small ResNet detect AI-generated images with state-of-the-art accuracy on many benchmarks.

  9. FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 4.0

    FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.

  10. Findings of the Counter Turing Test: AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 4.0

    A competition using a new 50k-image dataset found high accuracy in binary real-vs-AI detection but only modest success in identifying the exact generative model.

  11. Findings of the Counter Turing Test: AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 4.0

    The Counter Turing Test competition finds F1-scores above 0.83 for binary real-vs-AI classification but only 0.4986 at best for identifying the specific generative model.

  12. Adaptive Forensic Feature Refinement via Intrinsic Importance Perception

    cs.CV 2026-04 unverdicted novelty 4.0

    I2P adaptively selects the most discriminative layers from visual foundation models for synthetic image detection and constrains task updates to low-sensitivity parameter subspaces to improve specificity without harmi...

  13. OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction

    cs.LG 2026-04 unverdicted novelty 4.0

    Ontology-aware contrastive pretraining plus note-to-vitals distillation improves MIMIC ICU risk and length-of-stay prediction using only vital signs at inference.

  14. Findings of the Counter Turing Test: AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 3.0

    Binary AI vs. real image classification reaches F1 > 0.83 while identifying the exact generative model achieves a highest F1 of 0.4986 on the MS COCOAI dataset.

  15. Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges

    cs.CV 2025-02 unverdicted novelty 2.0

    A systematic review of fully AI-generated image detection that organizes prior work around dataset construction and artifact extraction methods based on inductive priors.