Utilizing Transfer Learning and Homomorphic Encryption in a Privacy Preserving and Secure Biometric Recognition System

Salem, Milad; Taheri, Shayan; Yuan, J.S.

doi:10.3390/computers8010003

Cited by 38 publications

(25 citation statements)

References 25 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We introduce Swarm Learning as a decentralized learning system with access to data stored locally that can replace the current paradigm of data sharing and centralized storage while preserving data privacy in cross-institutional research in a wide spectrum of biomedical disciplines. Furthermore, SL can easily inherit developments to further preserve privacy such as functional encryption 64 , or encrypted transfer learning approaches 65 .…”

Section: Discussionmentioning

confidence: 99%

Swarm Learning as a privacy-preserving machine learning approach for disease classification

Warnat-Herresthal

Schultze

Shastry

et al. 2020

Preprint

View full text Add to dashboard Cite

AbstractIdentification of patients with life-threatening diseases including leukemias or infections such as tuberculosis and COVID-19 is an important goal of precision medicine. We recently illustrated that leukemia patients are identified by machine learning (ML) based on their blood transcriptomes. However, there is an increasing divide between what is technically possible and what is allowed because of privacy legislation. To facilitate integration of any omics data from any data owner world-wide without violating privacy laws, we here introduce Swarm Learning (SL), a decentralized machine learning approach uniting edge computing, blockchain-based peer-to-peer networking and coordination as well as privacy protection without the need for a central coordinator thereby going beyond federated learning. Using more than 14,000 blood transcriptomes derived from over 100 individual studies with non-uniform distribution of cases and controls and significant study biases, we illustrate the feasibility of SL to develop disease classifiers based on distributed data for COVID-19, tuberculosis or leukemias that outperform those developed at individual sites. Still, SL completely protects local privacy regulations by design. We propose this approach to noticeably accelerate the introduction of precision medicine.

show abstract

Section: Discussionmentioning

confidence: 99%

Swarm Learning as a privacy-preserving machine learning approach for disease classification

Warnat-Herresthal

Schultze

Shastry

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Several approaches have been proposed on privacy preserving DNN models, data mining, biometric recognition systems, IoT environment and wireless sensor networks by many authors. Some of these approaches include the multiple objective particle swarm optimization technique that relies on density clustering approach to hide sensitive information (CMPSO) [41], DeepZeroID based on homomorphic encryption [42], hierarchical-clustering mechanism [43], and differential privacy [17,18]. The differentially private models sometimes performed learning on clean data and use either the Laplace mechanism or an exponential mechanism to preserve privacy in the model [10].…”

Section: Review Of Existing Privacy Preserving Modelsmentioning

confidence: 99%

A Neuron Noise-Injection Technique for Privacy Preserving Deep Neural Networks

Adesuyi

Kim

2020

Open Computer Science

View full text Add to dashboard Cite

AbstractData is the key to information mining that unveils hidden knowledge. The ability to revealed knowledge relies on the extractable features of a dataset and likewise the depth of the mining model. Conversely, several of these datasets embed sensitive information that can engender privacy violation and are subsequently used to build deep neural network (DNN) models. Recent approaches to enact privacy and protect data sensitivity in DNN models does decline accuracy, thus, giving rise to significant accuracy disparity between a non-private DNN and a privacy preserving DNN model. This accuracy gap is due to the enormous uncalculated noise flooding and the inability to quantify the right level of noise required to perturb distinct neurons in the DNN model, hence, a dent in accuracy. Consequently, this has hindered the use of privacy protected DNN models in real life applications. In this paper, we present a neuron noise-injection technique based on layer-wise buffered contribution ratio forwarding and ϵ-differential privacy technique to preserve privacy in a DNN model. We adapt a layer-wise relevance propagation technique to compute contribution ratio for each neuron in our network at the pre-training phase. Based on the proportion of each neuron’s contribution ratio, we generate a noise-tuple via the Laplace mechanism, and this helps to eliminate unwanted noise flooding. The noise-tuple is subsequently injected into the training network through its neurons to preserve privacy of the training dataset in a differentially private manner. Hence, each neuron receives right proportion of noise as estimated via contribution ratio, and as a result, unquantifiable noise that drops accuracy of privacy preserving DNN models is avoided. Extensive experiments were conducted based on three real-world datasets and their results show that our approach was able to narrow down the existing accuracy gap to a close proximity, as well outperforms the state-of-the-art approaches in this context.

show abstract

“…For the semi-honest model, the former protocol is secure under known-sample attack (KSA), and the latter one achieves the security under known-plaintext attack (KPA). Achieving both the requirements of data security and verifiability, Salem et al [273] proposed a privacy-preserving biometric recognition system. Based on the property of additive homomorphism, the recognition process is operated on the encrypted features.…”

Section: ) Biometric Authenticationmentioning

confidence: 99%

A Comprehensive Survey on Secure Outsourced Computation and Its Applications

et al. 2019

View full text Add to dashboard Cite

With the ever-increasing requirement of storage and computation resources, it is unrealistic for local devices (with limited sources) to implement large-scale data processing. Therefore, individuals or corporations incline to outsource their computation requirements to the cloud. However, data outsourcing brings security and privacy concerns to users when the cloud servers are not fully trusted. Recently, extensive research works are conducted, aiming at secure outsourcing schemes for diverse computational tasks via different technologies. In this survey, we provide a technical review and comparison of existing outsourcing schemes using diverse secure computation methods. Specifically, we begin the survey by describing security threats and requirements of secure outsourcing computation. Meanwhile, we introduce four secure techniques (i.e., secure multi-party computation, pseudorandom functions, software guard extensions, and perturbation approaches) and their related works. Then, we focus on the theories and evolution of homomorphic encryption, as well as the applications of the basic operations and application-specific tasks. Finally, we discuss the security and performance of existing works and give future directions in this field. INDEX TERMS Secure outsourced computing, privacy preserving, homomorphic encryption, secure outsourced machine learning, data processing.

show abstract

Utilizing Transfer Learning and Homomorphic Encryption in a Privacy Preserving and Secure Biometric Recognition System

Cited by 38 publications

References 25 publications

Swarm Learning as a privacy-preserving machine learning approach for disease classification

Swarm Learning as a privacy-preserving machine learning approach for disease classification

A Neuron Noise-Injection Technique for Privacy Preserving Deep Neural Networks

A Comprehensive Survey on Secure Outsourced Computation and Its Applications

Contact Info

Product

Resources

About