# Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images

arXiv: https://arxiv.org/abs/2510.10231 · HTML: https://mlsanity.com/paper/2510.10231/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 59 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2408.04840/) (2024)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://mlsanity.com/paper/2402.13929/) (2024)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer](https://mlsanity.com/paper/2505.22705/) (2025)
- [SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model](https://mlsanity.com/paper/2412.04292/) (2024)
- [LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2305.11116/) (2023)
- [SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://mlsanity.com/paper/2503.09641/) (2025)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [LEGION: Learning to Ground and Explain for Synthetic Image Detection](https://mlsanity.com/paper/2503.15264/) (2025)

## Built on by (most cited first, 8 of 8)

- [EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection](https://mlsanity.com/paper/2603.17343/) (2026)
- [GenShield: Unified Detection and Artifact Correction for AI-Generated Images](https://mlsanity.com/paper/2605.16122/) (2026)
- [Moir'e Video Authentication: A Physical Signature Against AI Video Generation](https://mlsanity.com/paper/2604.01654/) (2026)
- [Boosting Robust AIGI Detection with LoRA-based Pairwise Training](https://mlsanity.com/paper/2604.12307/) (2026)
- [Robustness of AI-Art Detectors under Generator Shift](https://mlsanity.com/paper/2608.11643/) (2026)
- [Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them](https://mlsanity.com/paper/2609.32763/) (2026)
- [RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2609.36822/) (2026)
- [EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment](https://mlsanity.com/paper/2610.14609/) (2026)

## Abstract (arXiv)

The rapid advancement of AI-generated content (AIGC) has enabled the synthesis of visually convincing images; however, many such outputs exhibit subtle semantic anomalies, including unrealistic object configurations, violations of physical laws, or commonsense inconsistencies, which compromise the overall plausibility of the generated scenes. Detecting these semantic-level anomalies is essential for assessing the trustworthiness of AIGC media, especially in AIGC image analysis, explainable deepfake detection and semantic authenticity assessment. In this paper, we formalize semantic anomaly detection and reasoning for AIGC images and introduce AnomReason, a large-scale benchmark with structured annotations as quadruples (Name, Phenomenon, Reasoning, Severity). Annotations are produced by a modular multi-agent pipeline (AnomAgent) with lightweight human-in-the-loop verification, enabling scale while preserving quality. At construction time, AnomAgent processed approximately 4.17,B GPT-4o tokens, providing scale evidence for the resulting structured annotations. We further show that models fine-tuned on AnomReason achieve consistent gains over strong vision-language baselines under our proposed semantic matching metric (textitSemAP and textitSemF1). Applications to explainable deepfake detection and semantic reasonableness assessment of image generators demonstrate practical utility. In summary, AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images. We will release code, metrics, data, and task-aligned models to support reproducible research on semantic authenticity and interpretable AIGC forensics.