Paper
SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images
Authors
Aayush Dhakal, Subash Khanal, Srikumar Sastry, Jacob Arndt, Philipe Ambrozio Dias, Dalton Lunga, Nathan Jacobs
Abstract
The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection using Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85\% accuracy and +69.62\% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All code and models will be released on HuggingFace and GitHub.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.20412v1</id>\n <title>SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images</title>\n <updated>2026-02-23T23:22:41Z</updated>\n <link href='https://arxiv.org/abs/2602.20412v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.20412v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection using Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85\\% accuracy and +69.62\\% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All code and models will be released on HuggingFace and GitHub.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-02-23T23:22:41Z</published>\n <arxiv:comment>Accepted to CVPR 2026</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Aayush Dhakal</name>\n </author>\n <author>\n <name>Subash Khanal</name>\n </author>\n <author>\n <name>Srikumar Sastry</name>\n </author>\n <author>\n <name>Jacob Arndt</name>\n </author>\n <author>\n <name>Philipe Ambrozio Dias</name>\n </author>\n <author>\n <name>Dalton Lunga</name>\n </author>\n <author>\n <name>Nathan Jacobs</name>\n </author>\n </entry>"
}