Privacy-preserving federated k-means for proactive caching in next generation cellular networks

Rapid advancement in technology has led to the use of biometric authentication in every field. In particular, from the past few years, iris recognition systems has gained overwhelming advancement over other biometric traits due to its stability and uniqueness. Directly storing the templates into a centralized server leads to privacy concerns. Many state-of-the-art iris authentication systems based on cancelable biometrics and bio-cryptosystems have been introduced to provide security for the iris templates. However, these works suffer from accuracy loss relative to unprotected systems, or they require auxiliary data (AD), which compromise the privacy of the templates and security of the system. To address this, we propose a novel privacy-preserving iris authentication using fully homomorphic encryption which ensures the confidentiality of the templates and restricts the leakage of data from the templates. Our method improves the recognition accuracy by generating rotation invariant iris codes and reduces the computational time by using the batching scheme. Our approach satisfies all the requirements specified in the ISO/IEC 24745 standard. The proposed method has experimented on four benchmark publicly available iris databases which illustrate that our method can be practically achievable with no loss in the accuracy and preserve the privacy of the iris templates. Our method encrypts and computes the Hamming distance of 2560-dimensional iris features in about 0.0185 seconds only with an equal error rate value of 0.19% for CASIA-V 1.0 database.

Privacy-preserving iris authentication using fully homomorphic encryption

k-means clustering and kNN classification based on negative databases

Multi-biometric systems have been widely accepted in various applications due to its capability to solve the limitations of unimodal systems. Directly storing the biometric templates into a centralised server leads to privacy concerns. In the past few years, many biometric authentication systems based on homomorphic encryption have been introduced to provide security for the templates. Most of the existing solutions rely on an implication of the assumption that the server is ‘honest-but-curious’. Therefore, the compromise of server results into the entire system vulnerability and fails to provide the integrity. To address this, we propose a novel multi-instance iris authentication system, BMIAE to deal with malicious attacks over the transmission channel and at the untrusted server. BMIAE encrypt the iris templates using ElGamal encryption to guarantee confidentiality and Smart contract running on a Blockchain helps to achieve the integrity of templates and matching result. BMIAE also addresses the limitations of using Blockchain for biometrics like privacy and expensive storage. To check the effectiveness and robustness, BMIAE has experimented on CASIA-V3-Interval, IITD and SDUMLA-HMT iris databases. Experimental results show that BMIAE provides improved accuracy, and eliminates the need to trust the centralised server when compared to the state-of-the-art approaches.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-bmt.2019.0169

BMIAE: blockchain-based multi-instance Iris authentication using additive ElGamal homomorphic encryption

Traditional content marketing methods resort grossly to market requirements but barely obtain relatively accurate marketing prediction under loads of requirements. Machine learning-based approaches nowadays are widely used in multiple fields as they involve a training process to deal with big data problems. In this paper, decision tree-based methods are introduced to the field of content marketing, and decision tree-based methods intrinsically follow the process of human decision making. Specifically, this paper considers a well-known method, called C4.5, which can deal well with continuous values. Based on four validation metrics, experimental results obtained from several machine learning-based methods indicate that the C4.5-based decision tree method has the ability to handle the content marketing dataset. The results show that the decision tree-based method can provide reasonable and accurate suggestions for content marketing.

/pdf/application-of-decision-tree-based-classification-algorithm-2k5vn4rc.pdf

Application of Decision Tree-Based Classification Algorithm on Content Marketing

Data mining has become very popular with the arrival of big data era, but it also raises privacy issues. Negative database (NDB) is a new type of data representation which stores the negative image of data and can protect privacy while supporting some basic data mining operations such as classification and clustering. However, the existing clustering algorithm upon NDBs is based on Hamming distance, when facing datasets which have many categories for each attribute, the encoded data will become very long and resulting in low computational efficiency. In this paper, we propose a privacy-preserving k-means clustering algorithm based on Euclidean distance upon NDBs. The main step of k-means algorithm is to calculate the distance between each record and cluster centers, in order to solve the problem of privacy disclosure in this step, we transform each record in database into an NDB and propose a method to estimate Euclidean distance from a binary string and an NDB. Our work opens up new ideas for data mining upon negative database.

Privacy-Preserving K-Means Clustering Upon Negative Databases

Nowadays, biometric recognition has been widely used in real-world applications, but it has also brought potential privacy threats to users. Iris template protection enables an effective iris recognition while protecting personal privacy. In this paper, we propose a method for iris template protection based on randomized response technique and aggregated block information. Specifically, the iris data are first permuted according to an application-specific parameter; next, the permuted data are flipped using the randomized response technique; finally, the result is divided into blocks, and the aggregated information (i.e., the sum of all bits) in each block is calculated and stored instead of original iris data for privacy protection. We demonstrate that the proposed method supports the shifting and masking strategies for enhancing recognition performance. Moreover, the proposed method satisfies the three privacy requirements prescribed in ISO/IEC 24745: irreversibility, revocability and unlinkability. Experimental results show that the proposed method could effectively maintain the recognition performance (w.r.t. the original iris recognition system without privacy protection) on the iris database CASIA-IrisV3-Interval.

Iris Template Protection Based on Randomized Response Technique and Aggregated Block Information

Negative survey is a promising method which can protect personal privacy while collecting sensitive data. Most of previous works focus on negative survey models with specific hypothesis, e.g., the probability of selecting negative categories follows the uniform distribution or Gaussian distribution. Moreover, as far as we know, negative survey is never conducted with manual selection in real world. In this paper, we carry out such a negative survey and find that the survey may not follow the previous hypothesis. And existing reconstruction methods like NStoPS and NStoPS-I perform poorly on the survey data. Therefore, we propose a method called NStoPS-MLE, which is based on the maximum likelihood estimation, for reconstructing useful information from the collected data. This method also uses background knowledge to enhance its performance. Experimental results show that our method can get more accurate aggregated results than previous methods.

Negative Survey with Manual Selection: A Case Study in Chinese Universities

The invention relates to a safe iris recognition method based on aggregation block information, comprising that a user C sends iris data to a server to determine whether the iris data is valid; if theiris data of the user C is valid, a server S locally divides the iris data into blocks, obtains the aggregation information of each module, and returns registration success information; the user C obtains the implemented iris data t', converts the iris data t' into an iris feature template x' according to the same conversion method in the registration process; the user C sends the iris feature template x' to the server S, the server S receives x' and compares the x' with an iris template in a database to calculate the distance between the iris feature template x' and the iris template, if thedistance between a certain iris template y and x' is less than a threshold R, then x' is considered a valid iris template, and the server S authorizes the user C to use system resources. The method can meet three basic safety requirements and can support shifting and masking strategies to obtain good recognition performance.

Xiaoyi Hu

Papers

k-means clustering and kNN classification based on negative databases

Privacy-Preserving K-Means Clustering Upon Negative Databases

Iris Template Protection Based on Randomized Response Technique and Aggregated Block Information

Negative Survey with Manual Selection: A Case Study in Chinese Universities

Safe iris recognition method based on aggregation block information