A context-based privacy preserving framework for wearable visual lifeloggers

Zarepour, Eisa; Hosseini, Mohammadreza Khajeh; Kanhere, Salil S.; Sowmya, Arcot

doi:10.1109/percomw.2016.7457057

Cited by 20 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zarepour et al [24] proposed a context privacy-preserving framework for a lifelogging sensor. The authors used a combination of human activity recognition, ambient environment detection, and sensitive subject detection modules to remove context privacy concerns.…”

Section: Privacy Content Removal Methodsmentioning

confidence: 99%

Selective Content Removal for Egocentric Wearable Camera in Nutritional Studies

Hassan

Sazonov

2020

IEEE Access

View full text Add to dashboard Cite

Research and innovation on wearable sensor technology has grown exponentially over this decade. The privacy-related concerns have grown in tandem. Automatic Ingestion Monitor v2 (AIM-2) is an egocentric camera and sensor that aids monitoring of individual diet and eating behavior by capturing still images throughout the day and using sensor data to detect eating. The images may be used to recognize foods being eaten, eating environment, and other behaviors and daily activities. At the same time, captured images may carry privacy concerning content such as (1) people in social eating and/or bystanders (i.e., bystander privacy); (2) sensitive documents that may appear on a computer screen in the view of AIM-2 (i.e., context privacy). Managing privacy concerns by discarding images potentially containing private content is not practical as many activities are performed socially or with the use of computing devices. Therefore, we propose an automatic, image redaction-based privacy protection by selective content removal based on semantic segmentation using a deep learning neural network. We prioritize removal of humans and display screens. A free-living dataset containing 1 day of data from 15 participants was used to develop and validate the proposed method. We used 331,614 augmented data from 9 participates and publicly available data for training. The proposed method was validated on data of 6 participants and reported bystander privacy removal with precision of 0.87 and recall of 0.94 and reported context privacy removal by precision and recall of 0.97 and 0.98. The results of the study showed that selective content removal using deep learning neural network is a much more desirable approach to address privacy concerns for an egocentric wearable camera.

show abstract

Section: Privacy Content Removal Methodsmentioning

confidence: 99%

Selective Content Removal for Egocentric Wearable Camera in Nutritional Studies

Hassan

Sazonov

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The major technic which protects input data is input sanitization (e.g., context-based sanitization [262], video sanitization [263]). Moreover, to protect the user's gesture secure gesture detection and recognition solution that sends only gesture events to the applications must be deployed (e.g., [264]).…”

Section: ) Attacks and Countermeasuresmentioning

confidence: 99%

Verticals in 5G MEC-Use Cases and Security Challenges

et al. 2021

View full text Add to dashboard Cite

5G is the fifth-generation cellular network satisfying the requirements IMT-2020 (International Mobile Telecommunications-2020) of the International Telecommunication Union. Mobile network operators started using it worldwide in 2019. Generally, 5G achieves exceptionally high values of performance parameters of access and transmission. The application of edge servers facilitated the implementation of such requirements of 5G, which resulted in 5G MEC (Multi-access Edge Computing) technology. Moreover, to optimize services for specific business applications, the concept of 5G vertical industries has been proposed. In this paper, we study how the application of the MEC technology affects the functioning of 5G MEC-based services. We consider twelve representative vertical industries of 5G MEC by presenting their essential characteristics, threats, vulnerabilities, and known attacks. Next, we analyze their functional properties, give efficiency patterns and identify the effect of applying the MEC technology in 5G on the resultant network's quality parameters to identify the expected security requirements. Finally, we identify the impact of classified threats on the 5G empowered vertical industries and identify the most sensitive cases to focus on their protection against network attacks in the first place.

show abstract

“…Apart from techniques using adversarial approach to protect sensitive information on sensor data, [19] proposes two privacy preserving mechanisms based on clustering algorithms called Hierarchical Agglomerative Clustering to compress amount of disclosed data so that the amount of sensitive information can be reduced. [37] in their case, develop a framework for images data made on wearable cameras that can protect sensitive information such as face, objects or locations thanks to a neural network that detects the sensitive objects which will then be blurred or deleted. Rather than focusing on re-idenfication, [6] investigate what data to share, in such a way that certain kinds of inferences cannot be down.…”

Section: Related Workmentioning

confidence: 99%

DySan: Dynamically Sanitizing Motion Sensor Data Against Sensitive Inferences through Adversarial Networks

Boutet

Frindel

Gambs

et al. 2021

Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security

View full text Add to dashboard Cite

With the widespread adoption of the quantified self movement, an increasing number of users rely on mobile applications to monitor their physical activity through their smartphones. However, granting applications a direct access to sensor data expose users to privacy risks. In particular, motion sensor data are usually transmitted to analytics applications hosted on the cloud, which leverages on machine learning models to provide feedback on their activity status to users. In this setting, nothing prevents the service provider to infer private and sensitive information about a user such as health or demographic attributes. To address this issue, we propose DySan, a privacy-preserving framework to sanitize motion sensor data against unwanted sensitive inferences (i.e., improving privacy) while limiting the loss of accuracy on the physical activity monitoring (i.e., maintaining data utility). Our approach is inspired from the framework of Generative Adversarial Networks to sanitize the sensor data for the purpose of ensuring a good trade-off between utility and privacy. More precisely, by learning in a competitive manner several networks, DySan is able to build models that sanitize motion data against inferences on a specified sensitive attribute (e.g., gender) while maintaining an accurate activity recognition. DySan builds various sanitizing models, characterized by different sets of hyperparameters in the global loss function, to propose a transfer learning scheme over time by dynamically selecting the model which provides the best utility and privacy trade-off according to the incoming data. Experiments conducted on real datasets demonstrate that DySan can drastically limit the gender inference up to 41% (from 98% with raw data to 57% with sanitized data) while only reducing the accuracy of activity recognition by 3% (from 95% with raw data to 92% with sanitized data).

show abstract

A context-based privacy preserving framework for wearable visual lifeloggers

Cited by 20 publications

References 9 publications

Selective Content Removal for Egocentric Wearable Camera in Nutritional Studies

Selective Content Removal for Egocentric Wearable Camera in Nutritional Studies

Verticals in 5G MEC-Use Cases and Security Challenges

DySan: Dynamically Sanitizing Motion Sensor Data Against Sensitive Inferences through Adversarial Networks

Contact Info

Product

Resources

About