In general, the cross-generator generalization and robustness against attacks are two main challenges in AI-generated image detection. To address this, we put forward a synthetic image detector (DTBF), a two-branch architecture followed by a jointly-optimized concatenation (JOC), aiming at capturing low-level artifacts and high-level semantics and dynamically fusing them to enhance the generalization and robustness. In the artifact-extracted branch (AE-branch), the local multi-direction binary-encoding patterns (LMBP) are customized to extract and encode the relationships among pixels within each sliding window, resulting in the LMBP distribution serving as a universal fingerprint to distinguish real/fake images. The dual-alignment guided semantic branch (DAS-branch), working as a supplement to AE-branch, designs global context-unrelated prompts and semantic-enhanced prompts to capture global semantic inconsistency and local patch anomalies, strengthening the generalization and robustness of DTBF. Finally, JOC dynamically fuses the two branches through concatenation to amplify the effectiveness of each branch, achieving better generalization and robustness. With the assistance of two complementary branches and JOC, our proposed DTBF significantly outperforms 12 state-of-the-art detectors on two publicly available datasets in terms of detection accuracy and robustness.
Shaowei Weng, Rui Li, Lifang Yu et al.· IEEE Signal Processing Lette...· 0 citations
The rapid advancement of large-scale generative models has accelerated the spread of highly deceptive AI-generated images, making generalized synthetic image detection a critical imperative. Existing forensic networks often struggle with cross-model generalization and realworld degradations due to their reliance on single-domain representations and conventional binary classification optimization. To overcome these limitations, we propose RNSIDNet, a novel forensic framework that achieves robust detection through enhanced RGB-Noise representation learning. Specifically, our method employs a dual-branch architecture where global RGB semantics, extracted by an attention-refined CLIP backbone, dynamically modulate highfrequency noise artifacts captured by Bayar convolutions via a Feature-wise Linear Modulation (FiLM) module. To further enhance the learned representations, we design a Hard Sample-aware Contrastive Learning (HSCL) strategy. By explicitly penalizing challenging training samples, HSCL reshapes the latent feature space to maximize the discriminative margin between pristine and synthetic domains. Extensive experiments across eight public benchmark datasets verify that our model achieves state-of-the-art performance, delivering superior generalization ability, robustness, and computational efficiency. Code and dataset will be publicly available on https://github.com/multimediaFor/RNSIDNet.
Zhen Li, Gang Cao, Tianyi Zhang et al.· 0 citations