Related papers: Content-based Graph Privacy Advisor

Content-based Graph Privacy Advisor

URL: http://arxiv.org/abs/2210.11169v1
Date: Thu, 20 Oct 2022 11:12:42 GMT
Title: Content-based Graph Privacy Advisor
Authors: Dimitrios Stoidis and Andrea Cavallaro
Abstract summary: We present an image privacy classifier that uses scene information and object cardinality as cues for the prediction of image privacy. Our Graph Privacy Advisor (GPA) model simplifies a state-of-the-art graph model and improves its performance.
Score: 38.733077459065704
License: http://creativecommons.org/licenses/by/4.0/
Abstract: People may be unaware of the privacy risks of uploading an image online. In this paper, we present an image privacy classifier that uses scene information and object cardinality as cues for the prediction of image privacy. Our Graph Privacy Advisor (GPA) model simplifies a state-of-the-art graph model and improves its performance by refining the relevance of the content-based information extracted from the image. We determine the most informative visual features to be used for the privacy classification task and reduce the complexity of the model by replacing high-dimensional image-based feature vectors with lower-dimensional, more effective features. We also address the biased prior information by modelling object co-occurrences instead of the frequency of object occurrences in each class.

Related papers

Image-guided topic modeling for interpretable privacy classification [27.301741710016223]
We propose to predict image privacy based on a set of natural language content descriptors. These content descriptors are associated with privacy scores that reflect how people perceive image content. We use the ITM-generated descriptors to learn a privacy predictor, Priv$times$ITM, whose decisions are interpretable by design.
arXiv Detail & Related papers (2024-09-27T12:02:28Z)
Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning [54.30994558765057]
The study pioneers a comprehensive privacy protection framework that safeguards image data privacy concurrently during data sharing and model publication. We propose an interactive image privacy protection framework that utilizes generative machine learning models to modify image information at the attribute level. Within this framework, we instantiate two modules: a differential privacy diffusion model for protecting attribute information in images and a feature unlearning algorithm for efficient updates of the trained model on the revised image dataset.
arXiv Detail & Related papers (2024-09-05T07:55:55Z)
Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
arXiv Detail & Related papers (2024-05-30T05:53:49Z)
Explaining models relating objects and privacy [33.78605193864911]
We evaluate privacy models that use objects extracted from an image to determine why the image is predicted as private. We show that the presence of the person category and its cardinality is the main factor for the privacy decision.
arXiv Detail & Related papers (2024-05-02T18:06:48Z)
Human-interpretable and deep features for image privacy classification [32.253391125106674]
We discuss suitable features for image privacy classification and propose eight privacy-specific and human-interpretable features. These features increase the performance of deep learning models and, on their own, improve the image representation for privacy classification compared with much higher dimensional deep features.
arXiv Detail & Related papers (2023-10-30T14:39:43Z)
Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network [92.01145655155374]
We present an unsupervised image enhancement generative network (UEGAN) It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner. Results show that the proposed model effectively improves the aesthetic quality of images.
arXiv Detail & Related papers (2020-12-30T03:22:46Z)
Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks [55.11806035788036]
It is advantageous to visualize the features considered to be essential for classification. Existing visualization methods develop high confidence images consisting of both background and foreground features. In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
arXiv Detail & Related papers (2020-07-31T06:11:06Z)
Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings [72.68801373979943]
Many computer vision systems require users to upload image features to the cloud for processing and storage. We propose a new privacy-preserving feature representation. Compared to the original features, our approach makes it significantly more difficult for an adversary to recover private information.
arXiv Detail & Related papers (2020-06-11T17:29:48Z)
Privacy-Preserving Image Classification in the Local Setting [17.375582978294105]
Local Differential Privacy (LDP) brings us a promising solution, which allows the data owners to randomly perturb their input to provide the plausible deniability of the data before releasing. In this paper, we consider a two-party image classification problem, in which data owners hold the image and the untrustworthy data user would like to fit a machine learning model with these images as input. We propose a supervised image feature extractor, DCAConv, which produces an image representation with scalable domain size.
arXiv Detail & Related papers (2020-02-09T01:25:52Z)

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