BOSC: A Backdoor-Based Framework for Open Set Synthetic Image Attribution

With the continuous progress of AI technology, new generative architectures continuously appear, thus driving the attention of researchers towards the development of synthetic image attribution methods capable of working in open-set scenarios. Existing approaches focus on extracting highly discrimin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on information forensics and security Jg. 20; S. 8043 - 8058
Hauptverfasser: Wang, Jun, Tondi, Benedetta, Barni, Mauro
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 2025
Schlagworte:
Analytical models
Autoencoders
backdoor injection
Computer architecture
deep learning for multimedia forensics
Facial features
Feature extraction
Image forensics
Image recognition
open set recognition
Prototypes
Robustness
Synthetic image attribution
Training
ISSN:1556-6013, 1556-6021
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the continuous progress of AI technology, new generative architectures continuously appear, thus driving the attention of researchers towards the development of synthetic image attribution methods capable of working in open-set scenarios. Existing approaches focus on extracting highly discriminative features for closed-set architectures, increasing the confidence of the prediction when the samples come from closed-set models/architectures, or estimating the distribution of unknown samples, i.e., samples from unknown architectures. In this paper, we propose a novel framework for open set attribution of synthetic images, named BOSC (Backdoor-based Open Set Classification), that relies on backdoor injection to design a classifier with rejection option. BOSC works by deliberately including class-specific triggers inside a portion of the images in the training set to induce the network to establish a matching between in-set class features and trigger features. The behavior of the trained model with respect to samples containing a trigger is then exploited at inference time to perform sample rejection using an ad-hoc score. Experiments show that the proposed method has good performance, always surpassing the state-of-the-art. Robustness against image processing is also very good. Although we designed our method for the task of synthetic image attribution, the proposed framework is a general one and can be used for other image forensic applications.
ISSN:1556-6013
1556-6021
DOI:10.1109/TIFS.2025.3592531