# WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution arXiv: https://arxiv.org/abs/2504.19595 · HTML: https://mlsanity.com/paper/2504.19595/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Builds on 28 of its 42 references that are in the map. - First posted on arXiv 28 Apr 2025. ## Builds on (most cited first, 28 of 28) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019) - [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018) - [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022) - [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016) - [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017) - [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018) - [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021) - [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018) - [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023) - [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021) - [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024) - [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023) - [Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://mlsanity.com/paper/2405.08748/) (2024) - [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018) - [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022) - [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023) - [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023) - [Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models](https://mlsanity.com/paper/2306.00637/) (2023) - [ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detection](https://mlsanity.com/paper/2302.11970/) (2023) - [GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusions](https://mlsanity.com/paper/2312.16220/) (2023) - [When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering](https://mlsanity.com/paper/2407.10736/) (2024) ## Built on by (most cited first, 9 of 9) - [Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning](https://mlsanity.com/paper/2508.21048/) (2025) - [ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attacks](https://mlsanity.com/paper/2601.18386/) (2026) - [ImageAttributionBench: How Far Are We from Generalizable Attribution?](https://mlsanity.com/paper/2605.12967/) (2026) - [Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection](https://mlsanity.com/paper/2510.05633/) (2025) - [Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery](https://mlsanity.com/paper/2511.04260/) (2025) - [μFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors](https://mlsanity.com/paper/2606.30528/) (2026) - [Face-Trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators](https://mlsanity.com/paper/2607.07545/) (2026) - [DNA: Dual-stage Native Attribution for Generated Image Source Tracing](https://mlsanity.com/paper/2607.13685/) (2026) - [Hybrid Semantic and Spectral Ensemble for Robust Synthetic Image Source Attribution](https://mlsanity.com/paper/2607.22808/) (2026) ## Abstract (arXiv) Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available generative techniques, as well as the scarcity of high-quality open source datasets of diverse nature for this task, make training and benchmarking synthetic image source attribution models very challenging. WILD is a new in-the-Wild Image Linkage Dataset designed to provide a powerful training and benchmarking tool for synthetic image attribution models. The dataset is built out of a closed set of 10 popular commercial generators, which constitutes the training base of attribution models, and an open set of 10 additional generators, simulating a real-world in-the-wild scenario. Each generator is represented by 1,000 images, for a total of 10,000 images in the closed set and 10,000 images in the open set. Half of the images are post-processed with a wide range of operators. WILD allows benchmarking attribution models in a wide range of tasks, including closed and open set identification and verification, and robust attribution with respect to post-processing and adversarial attacks. Models trained on WILD are expected to benefit from the challenging scenario represented by the dataset itself. Moreover, an assessment of seven baseline methodologies on closed and open set attribution is presented, including robustness tests with respect to post-processing.