A Novel Differential Privacy Approach that Enhances Classification Accuracy

The growth in the use of Information and Communications Technology (ICT) and Artificial intelligence (AI) has improved the productivity and efficiency of modern agriculture, which is commonly referred to as precision farming. Precision farming solutions are dependent on collecting a large amount of data from farms. Despite the many advantages of precision farming, security threats are a major challenge that is continuously on the rise and can harm various stakeholders in the agricultural system. These security issues may result in security breaches that could lead to unauthorized access to farmers' confidential data, identity theft, reputation loss, financial loss, or disruption to the food supply chain. Security breaches can occur because of an intentional or unintentional actions or incidents. Research suggests that humans play a key role in causing security breaches due to errors or system vulnerabilities. Farming is no different from other sectors. There is a growing need to protect data and IT assets on farms by raising awareness, promoting security best practices and standards, and embedding security practices into the systems. This paper provides recommendations for farmers on how they can mitigate potential security threats in precision farming. These recommendations are categorized into human-centric solutions, technology-based solutions, and physical aspect solutions. The paper also provides recommendations for Agriculture Technology Providers (ATPs) on best practices that can mitigate security risks.

show abstract

“…14. Use de-identification at source techniques from the first steps of data collection to protect farmers' privacy (Zaman et al, 2016).…”

Section: Security Practices Recommended To Agricultural Technology Pr...mentioning

confidence: 99%

On-Farm Data Security: Practical Recommendations for Securing Farm Data

Hazrati

Dara

Kaur

2022

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

show abstract

“…Zaman et al (19), after the inclusion of several noises in the data released, include an analysis to release data to classification purposes. Anonymous data generated by the current systems are, therefore, less useful [20]. Identity cannot be adequately covered, and the confidential release of knowledge cannot be accurately presented.…”

Section: Data Classificationmentioning

confidence: 99%

A General Framework Information Loss of Utility-Based Anonymization in Data Publishing

Ead¹

2021

TURCOMAT

View full text Add to dashboard Cite

To build anonymization, the data anonymizer must determine the following three issues: Firstly, which data to be preserved? Secondly, which adversary background knowledge used to disclosure the anonymized data? Thirdly, The usage of the anonymized data? We have different anonymization techniques from the previous three-question according to different adversary background knowledge and information usage (information utility). In other words, different anonymization techniques lead to different information loss. In this paper, we propose a general framework for the utility-based anonymization to minimize the information loss in data published with a trade-off grantee of achieving the required privacy level.

show abstract

“…Besides using popular metrics such as information loss, precision, and i i "main" -2021/4/15 -0:46 -page 5 -#5 i i i i i i discernability to measure utility, several works used the accuracy of a trained classification model as the utility metric. Such approaches lean towards employing machine learning (ML) models or decision trees to measure the accuracy-anonymization/privacy trade-off [111,52,28,54,48].…”

Section: Anonymization Of Relational Health Datamentioning

confidence: 99%

A Review of Anonymization for Healthcare Data

Olatunji,

Rauch,

Katzensteiner

et al. 2021

Preprint

View full text Add to dashboard Cite

Mining health data can lead to faster medical decisions, improvement in the quality of treatment, disease prevention, reduced cost, and it drives innovative solutions within the healthcare sector. However, health data is highly sensitive and subject to regulations such as the General Data Protection Regulation (GDPR), which aims to ensure patient's privacy. Anonymization or removal of patient identifiable information, though the most conventional way, is the first important step to adhere to the regulations and incorporate privacy concerns. In this paper, we review the existing anonymization techniques and their applicability to various types (relational and graph-based) of health data. Besides, we provide an overview of possible attacks on anonymized data. We illustrate via a reconstruction attack that anonymization though necessary, is not sufficient to address patient privacy and discuss methods for protecting against such attacks. Finally, we discuss tools that can be used to achieve anonymization.

show abstract

A Novel Differential Privacy Approach that Enhances Classification Accuracy

Cited by 19 publications

References 31 publications

On-Farm Data Security: Practical Recommendations for Securing Farm Data

On-Farm Data Security: Practical Recommendations for Securing Farm Data

A General Framework Information Loss of Utility-Based Anonymization in Data Publishing

A Review of Anonymization for Healthcare Data

Contact Info

Product

Resources

About