SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection

TL;DR

SPECTRA-Net is a scalable, explainable pipeline that combines multi-view tensor representations and spectral analysis to detect AI-generated images across diverse datasets with high accuracy.

Contribution

It introduces a novel multi-view, cross-domain tensor-based approach that enhances robustness and explainability in AI-generated image detection.

Findings

Achieves state-of-the-art accuracy in in-domain and cross-domain detection

Demonstrates high generalization across multiple challenging datasets

Provides explainability through artifact localization

Abstract

The rapid proliferation of AI-generated images (AIGI) presents a significant challenge to digital information integrity. While human observers and existing detection models struggle to keep pace with the increasing sophistication of generative models, the need for robust, real-time detection systems has become critical. This paper introduces SPECTRA-Net, a scalable pipeline for explainable, cross-domain tensor representations for AIGI detection. Our approach leverages a multi-view representation of images, combining global semantic features from a Vision Foundation Model (VFM), spectral analysis, local patch-based anomaly detection, and statistical descriptors. By fusing these complementary data streams, SPECTRA-Net achieves state-of-the-art performance in both in-domain and cross-domain settings, demonstrating high accuracy and generalization capabilities across a wide range of challenging datasets, including WildFake, Chameleon, and RRDataset. The proposed pipeline not only provides a robust solution for AIGI detection but also offers explainability through artifact localization, paving the way for more trustworthy and reliable content verification in real-world applications.