# Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection

arXiv: https://arxiv.org/abs/2312.10461 · HTML: https://mlsanity.com/paper/2312.10461/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 65 references that are in the map.
- First posted on arXiv 16 Dec 2023.

## Builds on (most cited first, 5 of 5)

- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [BEGAN: Boundary Equilibrium Generative Adversarial Networks](https://mlsanity.com/paper/1703.10717/) (2017)
- [The Cramer Distance as a Solution to Biased Wasserstein Gradients](https://mlsanity.com/paper/1705.10743/) (2017)

## Built on by (most cited first, 30 of 41)

- [C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection](https://mlsanity.com/paper/2408.09647/) (2024)
- [ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection](https://mlsanity.com/paper/2408.13697/) (2024)
- [Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook](https://mlsanity.com/paper/2411.19537/) (2024)
- [Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?](https://mlsanity.com/paper/2507.10236/) (2025)
- [Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning](https://mlsanity.com/paper/2508.01603/) (2025)
- [CausalCLIP: Causally-Informed Feature Disentanglement and Filtering for Generalizable Detection of Generated Images](https://mlsanity.com/paper/2512.13285/) (2025)
- [Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation](https://mlsanity.com/paper/2509.00428/) (2025)
- [LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors](https://mlsanity.com/paper/2511.07192/) (2025)
- [TextRich: A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2](https://mlsanity.com/paper/2606.19259/) (2026)
- [SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness](https://mlsanity.com/paper/2607.02886/) (2026)
- [Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection](https://mlsanity.com/paper/2607.15321/) (2026)
- [GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detection](https://mlsanity.com/paper/2509.10250/) (2025)
- [GlobalForge: Towards Robust AI-Generated Image Detection](https://mlsanity.com/paper/2607.14684/) (2026)
- [Grounding and Explaining Visual Evidence for AI-Generated Image Detection in Human-Centric Scenes](https://mlsanity.com/paper/2608.01988/) (2026)
- [SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data](https://mlsanity.com/paper/2608.12876/) (2026)
- [Anchor-Regularized Adaptation for Generalizable AI-Generated Image Detection with DINOv3](https://mlsanity.com/paper/2608.15196/) (2026)
- [Chameleon: Benchmarking Detection and Backtracking on Commercial-Grade AI-Generated Videos](https://mlsanity.com/paper/2503.06624/) (2025)
- [MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection](https://mlsanity.com/paper/2504.13726/) (2025)
- [High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking](https://mlsanity.com/paper/2603.23940/) (2026)
- [Generalizable Face Forgery Detection via Separable Prompt Learning](https://mlsanity.com/paper/2604.17307/) (2026)
- [Automated In-the-Wild Data Collection for Continual AI Generated Image Detection](https://mlsanity.com/paper/2605.02567/) (2026)
- [LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection](https://mlsanity.com/paper/2605.04445/) (2026)
- [Detecting AI-Generated Videos with Spiking Neural Networks](https://mlsanity.com/paper/2605.05895/) (2026)
- [ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors](https://mlsanity.com/paper/2607.21897/) (2026)
- [FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection](https://mlsanity.com/paper/2607.22087/) (2026)
- [DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection](https://mlsanity.com/paper/2607.27882/) (2026)
- [Test-Time Curriculum for Open-Set AIGC Detection](https://mlsanity.com/paper/2608.00559/) (2026)
- [V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors](https://mlsanity.com/paper/2608.03008/) (2026)
- [PatchHead: Learning Spatial Patch Evidence for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2608.09223/) (2026)
- [Structured Local Differential Modeling for AI-Generated Image Detection](https://mlsanity.com/paper/2608.12811/) (2026)

## Abstract (arXiv)

Recently, the proliferation of highly realistic synthetic images, facilitated through a variety of GANs and Diffusions, has significantly heightened the susceptibility to misuse. While the primary focus of deepfake detection has traditionally centered on the design of detection algorithms, an investigative inquiry into the generator architectures has remained conspicuously absent in recent years. This paper contributes to this lacuna by rethinking the architectures of CNN-based generators, thereby establishing a generalized representation of synthetic artifacts. Our findings illuminate that the up-sampling operator can, beyond frequency-based artifacts, produce generalized forgery artifacts. In particular, the local interdependence among image pixels caused by upsampling operators is significantly demonstrated in synthetic images generated by GAN or diffusion. Building upon this observation, we introduce the concept of Neighboring Pixel Relationships(NPR) as a means to capture and characterize the generalized structural artifacts stemming from up-sampling operations. A comprehensive analysis is conducted on an open-world dataset, comprising samples generated by tft28 distinct generative models. This analysis culminates in the establishment of a novel state-of-the-art performance, showcasing a remarkable tft11.6% improvement over existing methods. The code is available at https://github.com/chuangchuangtan/NPR-DeepfakeDetection.