Improving Synthetically Generated Image Detection in Cross-Concept Settings

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00371413" target="_blank" >RIV/68407700:21230/23:00371413 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1145/3592572.3592846" target="_blank" >https://doi.org/10.1145/3592572.3592846</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3592572.3592846" target="_blank" >10.1145/3592572.3592846</a>

Result language

angličtina

Original language name

Improving Synthetically Generated Image Detection in Cross-Concept Settings

Original language description

New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and speed. In this paper, we focus on the challenge of generalizing across different concept classes, e.g., when training a detector on human faces and testing on synthetic animal images - highlighting the ineffectiveness of existing approaches that randomly sample generated images to train their models. By contrast, we propose an approach based on the premise that the robustness of the detector can be enhanced by training it on realistic synthetic images that are selected based on their quality scores according to a probabilistic quality estimation model. We demonstrate the effectiveness of the proposed approach by conducting experiments with generated images from two seminal architectures, StyleGAN2 and Latent Diffusion, and using three different concepts for each, so as to measure the cross-concept generalization ability. Our results show that our quality-based sampling method leads to higher detection performance for nearly all concepts, improving the overall effectiveness of the synthetic image detectors.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

2nd ACM International Workshop on Multimedia AI against Disinformation (MAD '23)

ISBN

979-8-4007-0187-0

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

28-35

Publisher name

ACM

Place of publication

New York

Event location

Thessaloniki

Event date

Jun 12, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001059176200005