Leveraging Content Sensitiveness and User Trustworthiness to Recommend Fine-Grained Privacy Settings for Social Image Sharing

Yu, Jun; Kuang, Zhenzhong; Zhang, Baopeng; Zhang, Wei; Lin, Dan; Fan, Jianping

doi:10.1109/tifs.2017.2787986

Cited by 185 publications

(56 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, they use the outcomes of such model to identify the most suitable privacy settings and/or blur sensitive objects automatically. This framework is further improved in [24], where the authors add a clustering-based approach to also incorporate trustworthiness of users being granted to see the images in the prediction model. Contrary to the above-mentioned works, in this paper we formally define the general task of content sensitivity analysis independently from the type of data to be analyzed.…”

Section: Related Workmentioning

confidence: 99%

Towards Content Sensitivity Analysis

Battaglia

Bioglio

Pensa

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

With the availability of user-generated content in the Web, malicious users dispose of huge repositories of private (and often sensitive) information regarding a large part of the world's population. The self-disclosure of personal information, in the form of text, pictures and videos, exposes the authors of such contents (and not only them) to many criminal acts such as identity thefts, stalking, burglary, frauds, and so on. In this paper, we propose a way to evaluate the harmfulness of any form of content by defining a new data mining task called content sensitivity analysis. According to our definition, a score can be assigned to any object (text, picture, video...) according to its degree of sensitivity. Even though the task is similar to sentiment analysis, we show that it has its own peculiarities and may lead to a new branch of research. Thanks to some preliminary experiments, we show that content sensitivity analysis can not be addressed as a simple binary classification task.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards Content Sensitivity Analysis

Battaglia

Bioglio

Pensa

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…λ > 0 is the parameter to balance the influences of the two parts. The optimal solution to Equation (15), which is denoted as Q * 0 , naturally defines an affinity relationship that implies the pairwise similarities between features. In this way, the similarity S…”

Section: Fusion With Low-rank Representationmentioning

confidence: 99%

“…Traditional methods make use of multiple features by directly concatenating them, which is oversimplified. To solve this problem, researchers also apply manifold learning to combine different types of features [14,15].…”

Section: Introductionmentioning

confidence: 99%

Multiple Network Fusion with Low-Rank Representation for Image-Based Age Estimation

et al. 2018

View full text Add to dashboard Cite

Featured Application: The proposed method is used in biometric feature recognition of people. Abstract: Image-based age estimation is a challenging task since there are ambiguities between the apparent age of face images and the actual ages of people. Therefore, data-driven methods are popular. To improve data utilization and estimation performance, we propose an image-based age estimation method. Theoretically speaking, the key idea of the proposed method is to integrate multi-modal features of face images. In order to achieve it, we propose a multi-modal learning framework, which is called Multiple Network Fusion with Low-Rank Representation (MNF-LRR). In this process, different deep neural network (DNN) structures, such as autoencoders, Convolutional Neural Networks (CNNs), Recursive Neural Networks (RNNs), and so on, can be used to extract semantic information of facial images. The outputs of these neural networks are then represented in a low-rank feature space. In this way, feature fusion is obtained in this space, and robust multi-modal image features can be computed. An experimental evaluation is conducted on two challenging face datasets for image-based age estimation extracted from the Internet Move Database (IMDB) and Wikipedia (WIKI). The results show the effectiveness of the proposed MNF-LRR.

show abstract

“…Now-a-days such social imaging is more often for recruiting employees. Considering the career networking as a part of social event, such privacy is required in social networking while recruiting or searching for jobs on various web portals [23], [24]. Furthermore, we refrain ourselves to post check those clauses and agreements to verify the privacy preservation processes.…”

Section: Introductionmentioning

confidence: 99%

A Privacy Preserving Distributed Ledger Framework for Global Human Resource Record Management: The Blockchain Aspect

et al. 2020

View full text Add to dashboard Cite

Blockchain is a technology used with the series of users in peer-to-peer transactions to utilize the usability properties of the immutable data records. The distributed nature of this technology has given the wide acceptance to its range of applications in various sectors. Seeing the prospect of this new technology, we have chosen the field of human resource management as these data needs to be privacy preserving and confidential along with significant research value. Distributed ledger approach is a novel idea in this field of work specifically for the application of human resource records management. We have used a privacy preserving framework that provides a transparent system for human resource record management. Wallets are generated with organization id and outputting with public-private key pair along with privacy parameter mapping with hash. Keys are used to provide confidentiality, integrity and authentication. Smart contract uses distributed but converged decision with privacy level classification. Performance of the proposed work has been measured based on time, memory consumptions, failure point identification and read-write latencies. The analysis of the results confirms the efficiency of the system.

show abstract

Leveraging Content Sensitiveness and User Trustworthiness to Recommend Fine-Grained Privacy Settings for Social Image Sharing

Cited by 185 publications

References 51 publications

Towards Content Sensitivity Analysis

Towards Content Sensitivity Analysis

Multiple Network Fusion with Low-Rank Representation for Image-Based Age Estimation

A Privacy Preserving Distributed Ledger Framework for Global Human Resource Record Management: The Blockchain Aspect

Contact Info

Product

Resources

About