# A Bias-Free Training Paradigm for More General AI-generated Image Detection

arXiv: https://arxiv.org/abs/2412.17671 · HTML: https://mlsanity.com/paper/2412.17671/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 42 of its 60 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [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)
- [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)
- [Fourier Spectrum Discrepancies in Deep Network Generated Images](https://mlsanity.com/paper/1911.06465/) (2019)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Randomized Autoregressive Visual Generation](https://mlsanity.com/paper/2411.00776/) (2024)
- [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023)
- [Diffusion Probabilistic Model Made Slim](https://mlsanity.com/paper/2211.17106/) (2022)
- [C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection](https://mlsanity.com/paper/2408.09647/) (2024)
- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [Identifying and Mitigating the Security Risks of Generative AI](https://mlsanity.com/paper/2308.14840/) (2023)
- [Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection](https://mlsanity.com/paper/2402.19091/) (2024)
- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)

## Built on by (most cited first, 30 of 67)

- [Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable](https://mlsanity.com/paper/2505.14359/) (2025)
- [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](https://mlsanity.com/paper/2506.16802/) (2025)
- [Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection](https://mlsanity.com/paper/2501.15253/) (2025)
- [AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection](https://mlsanity.com/paper/2504.20865/) (2025)
- [Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes](https://mlsanity.com/paper/2512.12982/) (2025)
- [NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2508.01248/) (2025)
- [Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale](https://mlsanity.com/paper/2604.04634/) (2026)
- [Venus-DeFakerOne: Unified Fake Image Detection & Localization](https://mlsanity.com/paper/2605.14091/) (2026)
- [EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection](https://mlsanity.com/paper/2603.17343/) (2026)
- [PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.21207/) (2026)
- [So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection](https://mlsanity.com/paper/2505.18660/) (2025)
- [DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection](https://mlsanity.com/paper/2511.13108/) (2025)
- [Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.24906/) (2026)
- [Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges](https://mlsanity.com/paper/2502.19716/) (2025)
- [AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignment](https://mlsanity.com/paper/2512.06746/) (2025)
- [Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection](https://mlsanity.com/paper/2512.17350/) (2025)
- [Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction](https://mlsanity.com/paper/2602.06676/) (2026)
- [Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution](https://mlsanity.com/paper/2603.10583/) (2026)
- [AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection](https://mlsanity.com/paper/2603.23115/) (2026)
- [Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection](https://mlsanity.com/paper/2508.09475/) (2025)
- [Generalized Design Choices for Deepfake Detectors](https://mlsanity.com/paper/2511.21507/) (2025)
- [AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange](https://mlsanity.com/paper/2602.00192/) (2026)
- [Quality-Aware Calibration for AI-Generated Image Detection in the Wild](https://mlsanity.com/paper/2604.15027/) (2026)
- [The Synthetic Media Shift: Tracking the Rise, Virality, and Detectability of AI-Generated Multimodal Misinformation](https://mlsanity.com/paper/2604.15372/) (2026)
- [How Fragile Are Training-Free AI-Generated Image Detectors? A Controlled Audit of Score Direction, Preprocessing, and Compression](https://mlsanity.com/paper/2606.20488/) (2026)
- [DailyBench: A Unified Benchmark for AI-Generated and Manipulated Images from Modern Generative Models](https://mlsanity.com/paper/2607.24016/) (2026)
- [Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection](https://mlsanity.com/paper/2607.27113/) (2026)
- [Revealing the Implicit Noise-based Imprint of Generative Models](https://mlsanity.com/paper/2503.09314/) (2025)
- [Advance Fake Video Detection via Vision Transformers](https://mlsanity.com/paper/2504.20669/) (2025)
- [GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detection](https://mlsanity.com/paper/2509.10250/) (2025)

## Abstract (arXiv)

Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is largely due to inadequate training data quality. While most research focuses on developing new algorithms, less attention is given to training data selection, despite evidence that performance can be strongly impacted by spurious correlations such as content, format, or resolution. A well-designed forensic detector should detect generator specific artifacts rather than reflect data biases. To this end, we propose B-Free, a bias-free training paradigm, where fake images are generated from real ones using the conditioning procedure of stable diffusion models. This ensures semantic alignment between real and fake images, allowing any differences to stem solely from the subtle artifacts introduced by AI generation. Through content-based augmentation, we show significant improvements in both generalization and robustness over state-of-the-art detectors and more calibrated results across 27 different generative models, including recent releases, like FLUX and Stable Diffusion 3.5. Our findings emphasize the importance of a careful dataset design, highlighting the need for further research on this topic. Code and data are publicly available at https://grip-unina.github.io/B-Free/.