BIAS-ID is a new framework for analyzing transformation biases in AI-generated image detectors, with validation showing several state-of-the-art methods are strongly affected by such biases.
Raise: a raw images dataset for digital image forensics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
HFI detects LDM-generated images without training data by quantifying aliasing in autoencoder outputs and supports model-specific implicit watermarking.
citing papers explorer
-
BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors
BIAS-ID is a new framework for analyzing transformation biases in AI-generated image detectors, with validation showing several state-of-the-art methods are strongly affected by such biases.
-
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
HFI detects LDM-generated images without training data by quantifying aliasing in autoencoder outputs and supports model-specific implicit watermarking.