From Generation to Discrimination: Vision Foundation Models for Synthetic SEM Image Detection
Palangattu, A.; Sah, A. K.; Raman, S.; Pushpavanam, K. S.
Show abstract
In materials science, the integrity of scanning electron microscopy (SEM) images is paramount for quality control and validation of research outcomes. However, the introduction of sophisticated generative artificial intelligence, particularly Generative Adversarial Networks (GANs), has introduced a novel vulnerability: the potential for highly realistic, artificially synthesized SEM images to be used fraudulently in scientific literature. To address this challenge, we present a deep learning-based framework capable of distinguishing between authentic SEM images and those synthesized by Generative Adversarial Networks (GANs). Using FastGAN and StyleGAN2-ADA, two state-of-the-art GAN models, we generated synthetic SEM datasets to complement real imaging data. We fine-tuned a pre-trained Contrastive Language-Image Pre-training (CLIP) Vision Transformer (ViT-L-14) for binary classification. By unfreezing the final transformer blocks and appending a custom classification head, the model effectively captures the subtle, high-level artifacts inherent in GAN-generated upsampling. This work highlights the potential of deep learning to safeguard scientific imaging workflows and provides an important step toward detecting and mitigating image forgeries in materials science publications.
Matching journals
The top 11 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Adversarial erasing enhanced multiple instance learning (siMILe): Discriminative identification of oligomeric protein structures in single molecule localization microscopy 94%
- Label-free virtual peritoneal lavage cytology via deep-learning-assisted single-color stimulated Raman scattering microscopy 93%
- Assessing large multimodal models for one-shot learning and interpretability in biomedical image classification 92%
Similar papers in this journal
- Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity 92%
- His-MMDM: Multi-domain and Multi-omics Translation of Histopathology Images with Diffusion Models 92%
- High-throughput, label-free and slide-free histological imaging by computational microscopy and unsupervised learning 91%
Similar papers in this journal
- Neural-physics adaptive reconstruction reveals 3D subcellular nanostructures over a large depth of field 93%
- A deep learning-based stripe self-correction method for stitched microscopic images 92%
- A Petascale Automated Imaging Pipeline for Mapping Neuronal Circuits with High-throughput Transmission Electron Microscopy 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.