Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes

• URL: http://arxiv.org/abs/2304.06470v6
• Date: Thu, 20 Jun 2024 01:25:32 GMT
• Title: Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
• Authors: Ali Borji,
• Abstract summary: A gap remains between the quality of generated images and those found in the real world. By understanding these failures, we can identify areas where these models need improvement. The prevalence of deep fakes in today's society is a serious concern.
• Score: 43.37813040320147
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability of image and video generation models to create photorealistic images has reached unprecedented heights, making it difficult to distinguish between real and fake images in many cases. However, despite this progress, a gap remains between the quality of generated images and those found in the real world. To address this, we have reviewed a vast body of literature from both academic publications and social media to identify qualitative shortcomings in image generation models, which we have classified into five categories. By understanding these failures, we can identify areas where these models need improvement, as well as develop strategies for detecting deep fakes. The prevalence of deep fakes in today's society is a serious concern, and our findings can help mitigate their negative impact.

Related papers

• Can Generative Models Actually Forge Realistic Identity Documents? [51.56484100374058]
  Open-source and publicly accessible generative models can produce identity document forgeries.<n>Risk of generative identity document deepfakes achieving forensic-level authenticity may be overestimated.
  arXiv  Detail & Related papers  (2025-12-25T00:56:50Z)
• Perceptual Classifiers: Detecting Generative Images using Perceptual Features [28.667331253804214]
  Image Quality Assessment (IQA) models are employed in practical image and video processing pipelines to reduce storage, minimize transmission costs, and improve the Quality of Experience (QoE) of millions of viewers.<n>Recent advancements in generative models have resulted in a significant influx of "GenAI" content on the internet.<n>Here, we leverage the capabilities of existing IQA models, which effectively capture the manifold of real images within a bandpass statistical space, to distinguish between real and AI-generated images.
  arXiv  Detail & Related papers  (2025-07-23T06:18:09Z)
• A Watermark for Auto-Regressive Image Generation Models [50.599325258178254]
  We propose C-reweight, a distortion-free watermarking method explicitly designed for image generation models.<n>C-reweight mitigates retokenization mismatch while preserving image fidelity.
  arXiv  Detail & Related papers  (2025-06-13T00:15:54Z)
• KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities [93.74881034001312]
  We conduct a systematic study on the fidelity of entities in text-to-image generation models. We focus on their ability to generate a wide range of real-world visual entities, such as landmark buildings, aircraft, plants, and animals. Our findings reveal that even the most advanced text-to-image models often fail to generate entities with accurate visual details.
  arXiv  Detail & Related papers  (2024-10-15T17:50:37Z)
• Unveiling the Truth: Exploring Human Gaze Patterns in Fake Images [34.02058539403381]
  We leverage human semantic knowledge to investigate the possibility of being included in frameworks of fake image detection. A preliminary statistical analysis is conducted to explore the distinctive patterns in how humans perceive genuine and altered images.
  arXiv  Detail & Related papers  (2024-03-13T19:56:30Z)
• PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection [39.820699370876916]
  We propose a novel AI-generated image detector capable of identifying fake images created by a wide range of generative models. A novel Smash&Reconstruction preprocessing is proposed to erase the global semantic information and enhance texture patches. Our approach outperforms state-of-the-art baselines by a significant margin.
  arXiv  Detail & Related papers  (2023-11-21T07:12:40Z)
• Detecting Generated Images by Real Images Only [64.12501227493765]
  Existing generated image detection methods detect visual artifacts in generated images or learn discriminative features from both real and generated images by massive training. This paper approaches the generated image detection problem from a new perspective: Start from real images. By finding the commonality of real images and mapping them to a dense subspace in feature space, the goal is that generated images, regardless of their generative model, are then projected outside the subspace.
  arXiv  Detail & Related papers  (2023-11-02T03:09:37Z)
• Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep Image-to-Image Models against Adversarial Attacks [104.8737334237993]
  We present comprehensive investigations into the vulnerability of deep image-to-image models to adversarial attacks. For five popular image-to-image tasks, 16 deep models are analyzed from various standpoints. We show that unlike in image classification tasks, the performance degradation on image-to-image tasks can largely differ depending on various factors.
  arXiv  Detail & Related papers  (2021-04-30T14:20:33Z)
• Are GAN generated images easy to detect? A critical analysis of the state-of-the-art [22.836654317217324]
  With the increased level of photorealism, synthetic media are becoming hardly distinguishable from real ones. It is important to develop automated tools to reliably and timely detect synthetic media.
  arXiv  Detail & Related papers  (2021-04-06T15:54:26Z)
• What makes fake images detectable? Understanding properties that generalize [55.4211069143719]
  Deep networks can still pick up on subtle artifacts in doctored images. We seek to understand what properties of fake images make them detectable. We show a technique to exaggerate these detectable properties.
  arXiv  Detail & Related papers  (2020-08-24T17:50:28Z)
• Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data [64.65952078807086]
  Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs) Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual misinformation. We seek a proactive and sustainable solution on deepfake detection by introducing artificial fingerprints into the models.
  arXiv  Detail & Related papers  (2020-07-16T16:49:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.