Privacy-preserving machine learning with multiple data providers

Li, Ping; Li, Tong; Ye, Heng; Li, Jin; Chen, Xiaofeng; Xiang, Yang

doi:10.1016/j.future.2018.04.076

Cited by 80 publications

(29 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results of the illustrated method depict a 1% to 2% higher error rate and less accuracy as compared to the non-privacy preserving deep learning computational model. There are also some other related works that addressed the privacy protection issue in classification [84][85][86][87]. Because of the inefficiency problem with cryptographic solutions, there are also several related works presenting more efficient techniques including differential privacy [88][89][90].…”

Section: Privacy Preservationmentioning

confidence: 99%

Applications in Security and Evasions in Machine Learning: A Survey

2020

View full text Add to dashboard Cite

In recent years, machine learning (ML) has become an important part to yield security and privacy in various applications. ML is used to address serious issues such as real-time attack detection, data leakage vulnerability assessments and many more. ML extensively supports the demanding requirements of the current scenario of security and privacy across a range of areas such as real-time decision-making, big data processing, reduced cycle time for learning, cost-efficiency and error-free processing. Therefore, in this paper, we review the state of the art approaches where ML is applicable more effectively to fulfill current real-world requirements in security. We examine different security applications’ perspectives where ML models play an essential role and compare, with different possible dimensions, their accuracy results. By analyzing ML algorithms in security application it provides a blueprint for an interdisciplinary research area. Even with the use of current sophisticated technology and tools, attackers can evade the ML models by committing adversarial attacks. Therefore, requirements rise to assess the vulnerability in the ML models to cope up with the adversarial attacks at the time of development. Accordingly, as a supplement to this point, we also analyze the different types of adversarial attacks on the ML models. To give proper visualization of security properties, we have represented the threat model and defense strategies against adversarial attack methods. Moreover, we illustrate the adversarial attacks based on the attackers’ knowledge about the model and addressed the point of the model at which possible attacks may be committed. Finally, we also investigate different types of properties of the adversarial attacks.

show abstract

Section: Privacy Preservationmentioning

confidence: 99%

Applications in Security and Evasions in Machine Learning: A Survey

2020

View full text Add to dashboard Cite

show abstract

“…A la falta de formación y entrenamiento en análisis de datos (en técnicas para descripción, diagnóstico, predicción y prescripción) se suman los aspectos de seguridad de la información y protección de datos, de manera que la calidad de los datos internos y externos y su uso sean garantizados tanto para las empresas como para los potenciales clientes, como lo propone, ( Li, Li, Ye, Li, Chen & Xiang, 2018). La evolución de la computación cognitiva está permitiendo y permitirá cada vez con mayor incidencia una mejor toma de decisiones, gracias a los avances de las ciencias de los datos y su aplicación a la comercialización y el marketing.…”

Section: Conclusionesunclassified

Análisis de datos para el marketing digital emprendedor: Caso de estudio Parque de Innovación Empresarial - Universidad Nacional sede Manizales

Lopez

Trujillo

2020

Universidad&Empresa

View full text Add to dashboard Cite

El marketing digital o e-marketing ofrece diferentes oportunidades y beneficios que pueden ser aprovechadas por las pymes para mejorar su eficiencia y competitividad. Sin embargo, el desafío real es analizar los datos recopiladosy utilizarlos para optimizar procesos y recursos. A pesar de la considerable importancia que se le ha dado a este tema, se han realizado pocas investigaciones que unan los conceptos de e-marketing y análisis de datos en el contextoemprendedor. Este estudio se propuso explorar y describir el panorama del análisis de datos para el marketing digital en el Parque de Innovación Empresarial de Manizales, mediante la realización de 20 encuestas. En esta exploración,se encontró que los microempresarios reconocen la importancia y utilizan el marketing digital, pero solo la mitad de ellos realiza un análisis de datos superficial o básico, debido a diversas limitaciones que se expondrán. Se abren nuevas puertas para futuros estudios que tengan un enfoque de choque frente a la realidad encontrada.

show abstract

“…For example, the monitoring device should verify that the data actually came from the sensor at the specified location rather than being tampered with an attacker [28]. The traditional security and privacy policies based on asymmetric encryption are difficult to implement in an IoT environment, mainly due to the follow reasons:…”

Section: Problem Statementmentioning

confidence: 99%

Blockchain Based Credibility Verification Method for IoT Entities

Tao

Zhang

et al. 2018

Security and Communication Networks

View full text Add to dashboard Cite

With the fast development of mobile Internet, Internet of Things (IoT) has been found in many important applications recently. However, it still faces many challenges in security and privacy. Blockchain (BC) technology, which underpins the cryptocurrency Bitcoin, has played an important role in the development of decentralized and data intensive applications running on millions of devices. In this paper, to establish the relationship between IoT and BC for device credibility verification, we propose a framework with layers, intersect, and self-organization Blockchain Structures (BCS). In this new framework, each BCS is organized by Blockchain technology. We describe the credibility verification method and show how it provide the verification. The efficiency and security analysis are also given in this paper, including its response time, storage efficiency, and verification. The conducted experiments have been shown to demonstrate the validity of the proposed method in satisfying the credible requirement achieved by Blockchain technology and certain advantages in storage space and response time.

show abstract

Privacy-preserving machine learning with multiple data providers

Cited by 80 publications

References 13 publications

Applications in Security and Evasions in Machine Learning: A Survey

Applications in Security and Evasions in Machine Learning: A Survey

Análisis de datos para el marketing digital emprendedor: Caso de estudio Parque de Innovación Empresarial - Universidad Nacional sede Manizales

Blockchain Based Credibility Verification Method for IoT Entities

Contact Info

Product

Resources

About