Efficient privacy preservation of big data for accurate data mining

Chamikara, Mahawaga Arachchige Pathum; Bertók, Péter; Liu, Dongxi; Camtepe, Seyit; Khalil, Ibrahim

doi:10.1016/j.ins.2019.05.053

Cited by 76 publications

(68 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Newton et al proposed a de-identification approach for face images (named as k − same), which does not need complex cryptographic operations [10]. The proposed method is based on k − anonymity [6,22]. However, k − anonymity tends to reduce accuracy and increase information leak when introduced with high dimensional data [6].…”

Section: Related Workmentioning

confidence: 99%

Privacy Preserving Face Recognition Utilizing Differential Privacy

Chamikara

Bertók

Khalil

et al. 2020

Computers & Security

Self Cite

View full text Add to dashboard Cite

The published article can be found at https://doi.org/10. 1016/j.cose.2020.101951 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 thirdparty servers in an uncontrolled manner can be considered a significant privacy leak (i.e. uncontrolled information release) as biometrics can be correlated with sensitive data such as healthcare or financial records. In this paper, we propose a privacy-preserving technique for "controlled information release", where we disguise an original face image and prevent leakage of the biometric features while identifying a person. We introduce a new privacy-preserving face recognition protocol named PEEP (Privacy using EigEnface Perturbation) that utilizes local differential privacy. PEEP applies perturbation to Eigenfaces utilizing differential privacy and stores only the perturbed data in the third-party servers to run a standard Eigenface recognition algorithm. As a result, the trained model will not be vulnerable to privacy attacks such as membership inference and model memorization attacks. Our experiments show that PEEP exhibits a classification accuracy of around 70% -90% under standard privacy settings. individual face recognition for unlocking a mobile device to crowd surveillance. Companies have also invested heavily in this field; Google's facial recognition in the Google Glass project [1], Facebook's DeepFace technology [2], and Apple's patented face identification system [3] are examples of the growing number of facial identification systems. Existing face recognition technologies and the widespread use of biometrics introduce a serious threat to individuals' privacy, exacerbated by the fact that biometric identification is often done quietly, without proper consent from observed people. For example, the UK uses an estimated 4.2 million surveillance cameras to monitor public areas [4]. However, it is not feasible to obtain explicit consent from an extremely large number of persons being watched.Nevertheless, facial images directly reflect the owners' identity, and they can be easily linked to other sensitive information such as health records and financial records, raising privacy concerns. Biometric data analysis systems often need to employ high-performance third-party servers to conduct complex computational operations on large numbers of biometric data inputs. However, these third-party servers can be accessed by untrusted parties causing privacy issues.Among different definitions, information privacy can be defined as the "controlled information release" that permits an anticipated level of utility via a private function that protects the identity of the data owners [5]. Privacy-preserving face recognition involves at l...

show abstract

Section: Related Workmentioning

confidence: 99%

Privacy Preserving Face Recognition Utilizing Differential Privacy

Chamikara

Bertók

Khalil

et al. 2020

Computers & Security

Self Cite

View full text Add to dashboard Cite

show abstract

“…The anonymization-based study to protect individual privacy has become popular for the past decade. They conducted [16] a survey of U.S. census summary data to state the privacy risk of individuals.…”

Section: Related Workmentioning

confidence: 99%

Improving the Performance of Various Privacy Preserving Databases using Hybrid Geometric Data Perturbation Classification Model

Gouse¹,

Mohan²

2020

IJACSA

View full text Add to dashboard Cite

As the size of the privacy preserving databases is increasing, it is difficult to improve the privacy and accuracy of these databases due to dimensionality and runtime. However, most of the traditional privacy preserving models are independent of privacy and runtime. Also, it is essential to preserve the privacy of the large sensitive attributes before publishing it to the third-party servers. As a result, a novel framework is required to improve the privacy as well as accuracy on the high dimensional privacy preserving data with less runtime. In order to improve the privacy, accuracy and runtime of the traditional privacy preserving models, a hybrid perturbation based privacy preserving classification model is proposed on the multiple databases. In this work, a new data transformation approach, hybrid geometrical perturbation approach and hybrid boosting classifier are proposed in order to enhance the overall efficiency of the model on the privacy preserving databases. In this work, a hybrid geometric perturbation approach is used to enhance the privacy preserving on the sensitive attributes. Initially, a pre-processing method is applied on the input dataset in order to remove the noise in the feature values. A hybrid machine learning classifier is proposed to predict the privacy preserving class label based on the training data. Experimental results represents the proposed hybrid geometric perturbation based boosting classifier has better statistical accuracy, recall, precision and runtime than the conventional models.

show abstract

“…Such a lack of attention (Song et al, 2019) exposes organizations to information security breaches (Safa et al, 2016;Gordon et al, 2015). To defend themselves, organizations need to invest in information security, which is the protection of the organizational resources including information, hardware, or software (Chamikara et al, 2020;Guttman & Roback, 1995).…”

Section: Introductionmentioning

confidence: 99%

Information security in healthcare supply chains: an analysis of critical information protection practices

et al. 2020

View full text Add to dashboard Cite

Because of their vital role and the need to protect the patient information, interest in information security in Healthcare Supply Chains (HSCs) is growing. This study analyzes how decisions related to information security practices in HSCs contribute to protecting patient information. Eleven semi-structured interviews were performed. The interviewees were managers from Brazilian HSC organizations. Four dimensions and 14 variables identified in a literature review were used to perform categorical content analysis. The findings suggest organizations, while aware of their critical information and internal processes, lack the necessary metrics to measure the impacts of possible failures. It seems organizations tend to invest in standard security measures, while apparently ignoring the specificity and complexity of information in HSCs.

show abstract

Efficient privacy preservation of big data for accurate data mining

Cited by 76 publications

References 42 publications

Privacy Preserving Face Recognition Utilizing Differential Privacy

Privacy Preserving Face Recognition Utilizing Differential Privacy

Improving the Performance of Various Privacy Preserving Databases using Hybrid Geometric Data Perturbation Classification Model

Information security in healthcare supply chains: an analysis of critical information protection practices

Contact Info

Product

Resources

About