The reviewed record of science sign in
Pith

arxiv: 2312.00195 · v2 · pith:EVAWSR4K · submitted 2023-11-30 · cs.CV

Raising the Bar of AI-generated Image Detection with CLIP

Davide Cozzolino , Giovanni Poggi , Riccardo Corvi , Matthias Nie{\ss}ner , Luisa Verdoliva This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EVAWSR4Krecord.jsonopen to challenge →

classification cs.CV
keywords datadetectionai-generatedclipcontrarygeneralizationimagesrobustness
0
0 comments X
read the original abstract

The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios. We find that, contrary to previous beliefs, it is neither necessary nor convenient to use a large domain-specific dataset for training. On the contrary, by using only a handful of example images from a single generative model, a CLIP-based detector exhibits surprising generalization ability and high robustness across different architectures, including recent commercial tools such as Dalle-3, Midjourney v5, and Firefly. We match the state-of-the-art (SoTA) on in-distribution data and significantly improve upon it in terms of generalization to out-of-distribution data (+6% AUC) and robustness to impaired/laundered data (+13%). Our project is available at https://grip-unina.github.io/ClipBased-SyntheticImageDetection/

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 6 Pith papers

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

  1. A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2

    cs.CV 2026-06 unverdicted novelty 7.0

    Introduces a multi-domain benchmark for detecting AI-generated text-rich images from GPT-Image-2 and evaluates five detectors showing domain-dependent performance and JPEG sensitivity.

  2. LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    LEGO uses multiple generator-specific LoRA modules modulated by an MLP and fused with attention to detect synthetic images, achieving better performance than prior methods while using under 10% of the training data.

  3. Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?

    cs.CV 2025-07 conditional novelty 6.0

    The ITW-SM dataset and targeted optimization of detector design choices yield a 26.87% average AUC improvement for state-of-the-art AI-generated image detectors under real-world social media conditions.

  4. VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection

    cs.CV 2026-07 conditional novelty 5.0

    A 100-image cross-paradigm benchmark of 36 deepfake detectors reveals that ROC-AUC and MCC diverge sharply, meaning strong class-separation ranking does not guarantee reliable default-threshold decisions.

  5. Generative AI Literacy Training Improves Intelligence Analysts' Discrimination of Real and AI-Generated Images

    cs.HC 2026-06 conditional novelty 4.0

    A 30-minute training intervention increased US intelligence analysts' accuracy at distinguishing real from AI-generated images by 9 percentage points from a 72% baseline, mainly by improving identification of real images.

  6. Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation

    cs.CV 2026-05 unverdicted novelty 4.0

    Benchmarks Vision Mamba variants for AI-generated image detection against CNN, ViT, and VLM detectors on diverse datasets and synthetic sources, reporting promise alongside limitations.