# Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection arXiv: https://arxiv.org/abs/2509.12995 ยท HTML: https://mlsanity.com/paper/2509.12995/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 30 references that are in the map. - First posted on arXiv 16 Sep 2025. ## Builds on (most cited first, 26 of 26) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023) - [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023) - [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025) - [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025) - [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019) - [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023) - [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025) - [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023) - [Global Texture Enhancement for Fake Face Detection in the Wild](https://mlsanity.com/paper/2002.00133/) (2020) - [A Sanity Check for AI-generated Image Detection](https://mlsanity.com/paper/2406.19435/) (2024) - [Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2312.16649/) (2023) - [C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection](https://mlsanity.com/paper/2408.09647/) (2024) - [Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective](https://mlsanity.com/paper/2408.06741/) (2024) - [Meta CLIP 2: A Worldwide Scaling Recipe](https://mlsanity.com/paper/2507.22062/) (2025) - [Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable](https://mlsanity.com/paper/2505.14359/) (2025) - [Real-Time Deepfake Detection in the Real-World](https://mlsanity.com/paper/2406.09398/) (2024) - [Is Artificial Intelligence Generated Image Detection a Solved Problem?](https://mlsanity.com/paper/2505.12335/) (2025) - [Zero-Shot Detection of AI-Generated Images](https://mlsanity.com/paper/2409.15875/) (2024) - [Aligned Datasets Improve Detection of Latent Diffusion-Generated Images](https://mlsanity.com/paper/2410.11835/) (2024) - [All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning](https://mlsanity.com/paper/2504.01396/) (2025) - [Altogether: Image Captioning via Re-aligning Alt-text](https://mlsanity.com/paper/2410.17251/) (2024) - [Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection](https://mlsanity.com/paper/2506.00874/) (2025) - [VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models](https://mlsanity.com/paper/2503.06142/) (2025) - [FairAdapter: Detecting AI-generated Images with Improved Fairness](https://mlsanity.com/paper/2411.14755/) (2024) - [No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection](https://mlsanity.com/paper/2508.17346/) (2025) ## Built on by (most cited first, 10 of 10) - [DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection](https://mlsanity.com/paper/2511.12511/) (2025) - [DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection](https://mlsanity.com/paper/2511.13108/) (2025) - [MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations](https://mlsanity.com/paper/2601.21408/) (2026) - [HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild](https://mlsanity.com/paper/2604.03555/) (2026) - [LOGER: Local--Global Ensemble for Robust Deepfake Detection in the Wild](https://mlsanity.com/paper/2604.03558/) (2026) - [TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection](https://mlsanity.com/paper/2604.26772/) (2026) - [Unleashing the Potential of Vision-Language Models for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2608.04935/) (2026) - [Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection](https://mlsanity.com/paper/2608.18523/) (2026) - [Mind the Rift: Cross-Scale Coupling Mismatch for AI-Generated Video Detection](https://mlsanity.com/paper/2609.00742/) (2026) - [Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents](https://mlsanity.com/paper/2609.14352/) (2026) ## Abstract (arXiv) While specialized detectors for AI-generated images excel on curated benchmarks, they fail catastrophically in real-world scenarios, as evidenced by their critically high false-negative rates on `in-the-wild' benchmarks. Instead of crafting another specialized `knife' for this problem, we bring a `gun' to the fight: a simple linear classifier on a modern Vision Foundation Model (VFM). Trained on identical data, this baseline decisively `outguns' bespoke detectors, boosting in-the-wild accuracy by a striking margin of over 20%. Our analysis pinpoints the source of the VFM's `firepower': First, by probing text-image similarities, we find that recent VLMs (e.g., Perception Encoder, Meta CLIP2) have learned to align synthetic images with forgery-related concepts (e.g., `AI-generated'), unlike previous versions. Second, we speculate that this is due to data exposure, as both this alignment and overall accuracy plummet on a novel dataset scraped after the VFM's pre-training cut-off date, ensuring it was unseen during pre-training. Our findings yield two critical conclusions: 1) For the real-world `gunfight' of AI-generated image detection, the raw `firepower' of an updated VFM is far more effective than the `craftsmanship' of a static detector. 2) True generalization evaluation requires test data to be independent of the model's entire training history, including pre-training.