Open-source CLI, API, web UI, and reproducible benchmarks for probabilistic AI-generated image detection.
Synthetic Image Detection
Zero-shot AI-generated image detection using forensic self-descriptions. Trained only on real images, detects deepfakes from any generator. Official implementation. CVPR 2025.
SuSy is a Spatial-Based Synthetic Image Detection and Recognition Model, designed to detect synthetic images and attribute them to specific generative models. This repository provides the code and instructions to train and evaluate SuSy or your own model for synthetic image detection.
Code for evaluating specific, re-implemented synthetic image detectors.
Cheap, CPU-only AI-image detector (no GPU/PyTorch). A reproducible classical image-forensics pipeline with an optional, still-CPU CLIP (ONNX) neural probe — calibratable, benchmarked, and built to fold in stronger models as they get cheap. CLI, FastAPI, Docker.
MediaEval 2026 SynthIM Subtask A project for real vs synthetic image detection using EfficientNet-B0, ConvNeXt-Tiny, and ViT/CLIP, with Kaggle-based experiments, fixed evaluation, analysis scripts, and competition submission files.
Arquitetura híbrida clássico-quântica (VQC) para detecção de imagens sintéticas — Brazil Quantum Camp
Add a description, image, and links to the synthetic-image-detection topic page so that developers can more easily learn about it.
To associate your repository with the synthetic-image-detection topic, visit your repo's landing page and select "manage topics."