Fingerprints of Super Resolution Networks

• URL: http://arxiv.org/abs/2410.21653v1
• Date: Tue, 29 Oct 2024 01:44:39 GMT
• Title: Fingerprints of Super Resolution Networks
• Authors: Jeremy Vonderfecht, Feng Liu,
• Abstract summary: We extend this research to single image super-resolution (SISR) networks. We show that SISR networks with a high upscaling factor or trained using adversarial loss leave highly distinctive fingerprints.
• Score: 4.673285689826945
• License:
• Abstract: Several recent studies have demonstrated that deep-learning based image generation models, such as GANs, can be uniquely identified, and possibly even reverse-engineered, by the fingerprints they leave on their output images. We extend this research to single image super-resolution (SISR) networks. Compared to previously studied models, SISR networks are a uniquely challenging class of image generation model from which to extract and analyze fingerprints, as they can often generate images that closely match the corresponding ground truth and thus likely leave little flexibility to embed signatures. We take SISR models as examples to investigate if the findings from the previous work on fingerprints of GAN-based networks are valid for general image generation models. We show that SISR networks with a high upscaling factor or trained using adversarial loss leave highly distinctive fingerprints, and that under certain conditions, some SISR network hyperparameters can be reverse-engineered from these fingerprints.

Related papers

• ASAP: Interpretable Analysis and Summarization of AI-generated Image Patterns at Scale [20.12991230544801]
  Generative image models have emerged as a promising technology to produce realistic images. There is growing demand to empower users to effectively discern and comprehend patterns of AI-generated images. We develop ASAP, an interactive visualization system that automatically extracts distinct patterns of AI-generated images.
  arXiv  Detail & Related papers  (2024-04-03T18:20:41Z)
• RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model [93.8067369210696]
  Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions. Diffusion models are one prominent type of generative model used for the generation of images through the systematic introduction of noises with repeating steps. In the era of large models, scaling up model size and the integration with large language models have further improved the performance of TTI models.
  arXiv  Detail & Related papers  (2023-09-02T03:27:20Z)
• Comparative analysis of segmentation and generative models for fingerprint retrieval task [0.0]
  Fingerprints deteriorate in quality if the fingers are dirty, wet, injured or when sensors malfunction. This paper proposes a deep learning approach to address these issues using Generative (GAN) and models. In our research, the u-net model performed better than the GAN networks.
  arXiv  Detail & Related papers  (2022-09-13T17:21:14Z)
• Generative Adversarial Networks for Image Super-Resolution: A Survey [49.567332038602785]
  Single image super-resolution (SISR) has played an important role in the field of image processing. Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples. In this paper, we conduct a comparative study of GANs from different perspectives.
  arXiv  Detail & Related papers  (2022-04-28T16:35:04Z)
• Self-supervised GAN Detector [10.963740942220168]
  generative models can be abused with malicious purposes, such as fraud, defamation, and fake news. We propose a novel framework to distinguish the unseen generated images outside of the training settings. Our proposed method is composed of the artificial fingerprint generator reconstructing the high-quality artificial fingerprints of GAN images.
  arXiv  Detail & Related papers  (2021-11-12T06:19:04Z)
• Discovering "Semantics" in Super-Resolution Networks [54.45509260681529]
  Super-resolution (SR) is a fundamental and representative task of low-level vision area. It is generally thought that the features extracted from the SR network have no specific semantic information. Can we find any "semantics" in SR networks?
  arXiv  Detail & Related papers  (2021-08-01T09:12:44Z)
• Fingerprinting Image-to-Image Generative Adversarial Networks [53.02510603622128]
  Generative Adversarial Networks (GANs) have been widely used in various application scenarios. This paper presents a novel fingerprinting scheme for the Intellectual Property protection of image-to-image GANs based on a trusted third party.
  arXiv  Detail & Related papers  (2021-06-19T06:25:10Z)
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images [36.08924910193875]
  State-of-the-art (SOTA) Generative Models (GMs) can synthesize photo-realistic images that are hard for humans to distinguish from genuine photos. We propose reverse engineering of GMs to infer model hyper parameters from the images generated by these models. We show that our fingerprint estimation can be leveraged for deepfake detection and image attribution.
  arXiv  Detail & Related papers  (2021-06-15T04:19:26Z)
• The FaceChannel: A Fast & Furious Deep Neural Network for Facial Expression Recognition [71.24825724518847]
  Current state-of-the-art models for automatic Facial Expression Recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We demonstrate how our model achieves a comparable, if not better, performance to the current state-of-the-art in FER.
  arXiv  Detail & Related papers  (2020-09-15T09:25:37Z)
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs [73.27299786083424]
  We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models. We first find that GANs learn various semantics in some linear subspaces of the latent space. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
  arXiv  Detail & Related papers  (2020-05-18T18:01:22Z)

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.