mlsanityData to 14 Oct 2026

VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systems

arXiv 2507.05146 ↗First posted 7 Jul 2025cs.CV cs.LGcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

The widespread and rapid adoption of AI-generated content, created by models such as Generative Adversarial Networks (GANs) and Diffusion Models, has revolutionized the digital media landscape by allowing efficient and creative content generation. However, these models also blur the difference between real images and AI-generated synthetic images, raising concerns regarding content authenticity and integrity. While many existing solutions to detect fake images focus solely on classification and higher-resolution images, they often lack transparency in their decision-making, making it difficult for users to understand why an image is classified as fake. In this paper, we present VERITAS, a comprehensive framework that not only accurately detects whether a small (32x32) image is AI-generated but also explains why it was classified that way through artifact localization and semantic reasoning. VERITAS produces human-readable explanations that describe key artifacts in synthetic images. We show that this architecture offers clear explanations of the basis of zero-shot synthetic image detection tasks. Code and relevant prompts can be found at https://github.com/V-i-g-n-e-s-h-N/VERITAS .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 85 of its 113 references that are in the map. First posted on arXiv 7 Jul 2025.

Builds on

85 of 113 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Explainable Synthetic Image Detection through Diffusion Timestep Ensembling8 Mar
  2. 2024Bi-LORA: A Vision-Language Approach for Synthetic Image Detection2 Apr
  3. 2024CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection20 Feb

Other references · 82

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  8. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  10. 2013Intriguing properties of neural networkscited by 5,155
  11. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  12. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
38 more
  1. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  3. 2016Adversarial examples in the physical worldcited by 1,769
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  8. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  9. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,062
  10. 2020Pre-Trained Image Processing Transformercited by 893
  11. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  12. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  13. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  14. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  15. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 625
  16. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 523
  17. 2017Countering Adversarial Images using Input Transformationscited by 520
  18. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  19. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  20. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 477
  21. 2013Do Deep Nets Really Need to be Deep?cited by 474
  22. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 329
  23. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  24. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 287
  25. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 278
  26. 2020What makes fake images detectable? Understanding properties that generalizecited by 273
  27. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  28. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  29. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  30. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 226
  31. 2021VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioningcited by 191
  32. 2019Adversarial Robustness through Local Linearizationcited by 146
  33. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  34. 2023M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuningcited by 126
  35. 2023PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detectioncited by 122
  36. 2023CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Imagescited by 84
  37. 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 82
  38. 2019Unmasking DeepFakes with simple Featurescited by 78

50 most cited of 82 All 82 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AI
  2. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
  3. 2025Explainable Detection of AI-Generated Images with Artifact Localization Using Faster-Than-Lies and Vision-Language Models for Edge Devices
  4. 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection
  5. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
  6. 2025SFLD: Reducing the content bias for AI-generated Image Detection
  7. 2025Beyond Known Fakes: Generalized Detection of AI-Generated Images via Post-hoc Distribution Alignment
  8. 2025So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection