Privacy Preserving Face Recognition Utilizing Differential Privacy

@article{MahawagaArachchige2020PrivacyPF,
  title={Privacy Preserving Face Recognition Utilizing Differential Privacy},
  author={Pathum Chamikara Mahawaga Arachchige and Peter Bert{\'o}k and Ibrahim Khalil and D. Liu and Seyit Ahmet Çamtepe},
  journal={Comput. Secur.},
  year={2020},
  volume={97},
  pages={101951}
}
Abstract Facial recognition technologies are implemented in many areas, including but not limited to, citizen surveillance, crime control, activity monitoring, and facial expression evaluation. However, processing biometric information is a resource-intensive task that often involves third-party servers, which can be accessed by adversaries with malicious intent. Biometric information delivered to untrusted third-party servers in an uncontrolled manner can be considered a significant privacy… Expand
Differentially Private Clustering via Maximum Coverage
TLDR
This paper examines differentially private variants of the k-medians and Euclidean k-means problems and presents polynomial algorithms with constant multiplicative error and lower additive error than the previous state-of-the-art for each problem. Expand
A Hybrid Enhanced Real-Time Face Recognition Model using Machine Learning Method with Dimension Reduction
Face recognition techniques play a crucial role in numerous disciplines of data security, verification, and authentication. The face recognition algorithm selects a face attribute from an imageExpand
A bio-inspired privacy-preserving framework for healthcare systems
TLDR
A novel framework for an effective utilization of sharable resources, which are available within the reachable region, is proposed by creating an opportunity to frame an opportunistic computing while preserving the user’s privacy. Expand
Analysis of Application Examples of Differential Privacy in Deep Learning
  • Zhidong Shen, Ting Zhong
  • Medicine
  • Computational intelligence and neuroscience
  • 2021
TLDR
This paper comparatively analyze and classify several deep learning models under differential privacy, and pays attention to the application of differential privacy in Generative Adversarial Networks (GANs), comparing and analyzing these models. Expand
Anonymous Access Monitoring of Indoor Areas
TLDR
This paper designs a novel privacy-preserving architecture able to anonymously monitoring people access at the entrance of critical areas in an indoor space and is able to provide full accountability in case of an accident or a legal requirement. Expand
Differential Privacy for Industrial Internet of Things: Opportunities, Applications, and Challenges
TLDR
This article conducts a comprehensive survey on the opportunities, applications, and challenges of differential privacy in IIoT, and focuses on the metrics of industrial data privacy, and analyze the contradiction between data utilization for deep models and individual privacy protection. Expand
Differentially Private ADMM Algorithms for Machine Learning
TLDR
Comparing the privacy-utility tradeoff of the two proposed algorithms shows that DP-AccADMM converges faster and has a better utility than DP-ADMM, when the privacy budget $\epsilon$ is larger than a threshold. Expand
Differentially Private Linear Regression Analysis via Truncating Technique
  • Yifei Liu, Ning Wang, +5 authors Jun Qiao
  • Computer Science
  • WISA
  • 2021
Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval
TLDR
A novel differentially private method PrivateMail is presented for supervised manifold learning, the first of its kind to the authors' knowledge, and a novel private geometric embedding scheme is provided for this experimental use case. Expand
Facial Recognition for Remote Electronic Voting â€" Missing Piece of the Puzzle or Yet Another Liability?
TLDR
This paper takes a closer look at facial recognition as a possible remote voter identification measure, covering technical aspects of facial recognition relevant to voting, the main architectural decisions, and some of the remaining open problems, including dispute resolution and privacy issues. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 59 REFERENCES
A
  • Roth, et al., The algorithmic foundations of differential privacy, Foundations and Trends R © in Theoretical Computer Science 9 (3–4)
  • 2014
Face recognition: eigenface
  • elastic matching, and neural nets, Proceedings of the IEEE 85 (9)
  • 1997
Privacy Preserving Distributed Machine Learning with Federated Learning
TLDR
DISTPAB alleviates computational bottlenecks by distributing the task of privacy preservation utilizing the asymmetry of resources of a distributed environment, which can have resource-constrained devices as well as high-performance computers. Expand
d.
TLDR
The novel JEV RT-NASBA assay could be used as an efficient molecular biology tool to diagnose JEV, which would facilitate the surveillance of reproductive failure disease in swine and would be beneficial for public health security. Expand
A Trustworthy Privacy Preserving Framework for Machine Learning in Industrial IoT Systems
TLDR
This article introduces a framework named PriModChain that enforces privacy and trustworthiness on IIoT data by amalgamating differential privacy, federated ML, Ethereum blockchain, and smart contracts. Expand
Efficient privacy preservation of big data for accurate data mining
TLDR
Experiments show that PABIDOT excels in execution speed, scalability, attack resistance, and accuracy in large-scale privacy- Preserving data classification when compared with two other, related privacy-preserving algorithms. Expand
Local Differential Privacy for Deep Learning
TLDR
A new local differentially private (LDP) algorithm named LATENT is proposed that redesigns the training process and enables a data owner to add a randomization layer before data leave the data owners’ devices and reach a potentially untrusted machine learning service. Expand
PE-MIU: A Training-Free Privacy-Enhancing Face Recognition Approach Based on Minimum Information Units
TLDR
PE-MIU is a privacy-enhancement approach for face recognition templates that achieves strong privacy-improvements and is not limited to pre-defined attributes and is able to achieve a verification performance close to that of the unmodified recognition system. Expand
An Efficient and Scalable Privacy Preserving Algorithm for Big Data and Data Streams
TLDR
A new data perturbation algorithm, SEAL (Secure and Efficient data perturbedation Algorithm utilizing Local differential privacy), is proposed, based on Chebyshev interpolation and Laplacian noise, which provides a good balance between privacy and utility with high efficiency and scalability. Expand
Lightweight Privacy-Preserving Ensemble Classification for Face Recognition
TLDR
This paper proposes a lightweight privacy-preserving adaptive boosting (AdaBoost) classification framework for face recognition (POR) based on the additive secret sharing and edge computing and proves the correctness and security of the protocols by theoretic analysis. Expand
...
1
2
3
4
5
...