paper-with-me

홈 › Papers

Privacy-Preserving Visual Content Tagging using Graph Transformer Networks

2020-10-20 · Xuan-Son Vu, Duc-Trong Le, Christoffer Edlund, Lili Jiang, Hoang D. Nguyen

With the rapid growth of Internet media, content tagging has become an important topic with many multimedia understanding applications, including efficient organisation and search. Nevertheless, existing visual tagging approaches are susceptible to inherent privacy risks in which private information may be exposed unintentionally. The use of anonymisation and privacy-protection methods is desirable, but with the expense of task performance. Therefore, this paper proposes an end-to-end framework (SGTN) using Graph Transformer and Convolutional Networks to significantly improve classification and privacy preservation of visual data. Especially, we employ several mechanisms such as differential privacy based graph construction and noise-induced graph transformation to protect the privacy of knowledge graphs. Our approach unveils new state-of-the-art on MS-COCO dataset in various semi-supervised settings. In addition, we showcase a real experiment in the education domain to address the automation of sensitive document tagging. Experimental results show that our approach achieves an excellent balance of model accuracy and privacy preservation on both public and private datasets.

📄 PDF Abstract BibTeX

Code (1)

ReML-AI/sgtn pytorch

Tasks

graph constructionKnowledge GraphsPrivacy Preserving

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Privacy-Preserving Visual Content Tagging using Graph Transformer Networks

2020-10-20 · Xuan-Son Vu, Duc-Trong Le, Christoffer Edlund, Lili Jiang 외

With the rapid growth of Internet media, content tagging has become an important topic with many multimedia understanding applications, including efficient organisation and search. Nevertheless, existing visual tagging a…

graph constructionKnowledge GraphsPrivacy Preserving

An Investigation towards Differentially Private Sequence Tagging in a Federated Framework

2021-06-01 · NAACL (PrivateNLP) 2021 6 · Abhik Jana, Chris Biemann

To build machine learning-based applications for sensitive domains like medical, legal, etc. where the digitized text contains private information, anonymization of text is required for preserving privacy. Sequence taggi…

Federated Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection

2025-11-16 · Jiayi Zhu, Yihao Huang, Yue Cao, Xiaojun Jia 외 arxiv

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversa…

On Content-Based Recommendation and User Privacy in Social-Tagging Systems

2016-05-20 · Puglisi Silvia, Parra-Arnau Javier, Forné Jordi, Rebollo-Monedero David

Recommendation systems and content filtering approaches based on annotations and ratings, essentially rely on users expressing their preferences and interests through their actions, in order to provide personalised conte…

Recommendation SystemsTAG

CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research

2026-04-08 · Carlos Caetano, Camila Laranjeira, Clara Ernesto, Artur Barros 외 arxiv

Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethical restrictions that prevent the public sharing of CSAI datasets. Thi…