arXiv Machine Learning August 11, 2026 By Maan Qraitem, Kate Saenko, Bryan A. Plummer

From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition

Read the original on arXiv Machine Learning →

arXiv:2308. 04553v4 Announce Type: replace-cross Abstract: Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions $B$ (\eg, Indoors) are over-represented in certain classes $Y$ (\eg, Big Dogs).

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computer Vision

Aug 25

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection

arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...

By Yichen Jiang, Mohammed Talha Alam, Sohail Ahmed Khan, Duc-Tien Dang-Nguyen, Fakhri Karray

llms diffusion fine-tuning benchmarks safety

arXiv AI

Jul 7

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

arXiv:2607. 02637v1 Announce Type: cross Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models.

By Disheng Liu, Tuo Liang, Chaoda Song, Yu Yin

llms computer-vision fine-tuning benchmarks safety

arXiv Machine Learning

Jun 30

$\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors

arXiv:2606. 30528v1 Announce Type: cross Abstract: Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy and security.

By Orazio Pontorno, Mattia Litrico, Luca Guarnera, Mario Valerio Giuffrida, Sebastiano Battiato

diffusion benchmarks safety

arXiv Computer Vision

Sep 17

Towards Generalizable Deepfake Detection via Real Distribution Bias Correction

arXiv:2603.14005v2 Announce Type: replace Abstract: To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using...

By Ming-Hui Liu, Harry Cheng, Xin Luo, Xin-Shun Xu, Mohan S. Kankanhalli

benchmarks safety

arXiv Machine Learning

Jun 16

Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction

arXiv:2605. 09697v3 Announce Type: replace-cross Abstract: In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a severe scarcity of positive samples.

By Radhika Amar Desai, Modigari Narendra

rag computer-vision data-engineering

arXiv Machine Learning

Aug 4

Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection

arXiv:2608. 00716v1 Announce Type: cross Abstract: Robust detection of generated images is critical to counter the misuse of generative models.

By Jun Nie, Yonggang Zhang, Tongliang Liu, Yiu-ming Cheung, Bo Han, Xinmei Tian

benchmarks

One email a morning, machine-written

Related stories

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

$\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors

Towards Generalizable Deepfake Detection via Real Distribution Bias Correction

Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction

Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection