• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.647-654
• /
• 2023

Deep Learning is a useful method for classifying and recognizing complex data such as images and text, and the accuracy of the deep learning method is the basis for making artificial intelligence-based services on the Internet useful. However, the vast amount of user da vita used for training in deep learning has led to privacy violation problems, and it is worried that companies that have collected personal and sensitive data of users, such as photographs and voices, own the data indefinitely. Users cannot delete their data and cannot limit the purpose of use. For example, data owners such as medical institutions that want to apply deep learning technology to patients' medical records cannot share patient data because of privacy and confidentiality issues, making it difficult to benefit from deep learning technology. In this paper, we have designed a privacy preservation technique-applied deep learning technique that allows multiple workers to use a neural network model jointly, without sharing input datasets, in multi-party system. We proposed a method that can selectively share small subsets using an optimization algorithm based on modified stochastic gradient descent, confirming that it could facilitate training with increased learning accuracy while protecting private information.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.3
• /
• pp.383-393
• /
• 2013

Data stream mining is a technique to obtain the useful information by analyzing the data generated in real time. In data stream mining technology, frequent itemset mining is a method to find the frequent itemset while data is transmitting, and these itemsets are used for the purpose of pattern analyze and marketing in various fields. Existing techniques of finding frequent itemset mining are having problems when a malicious attacker sniffing the data, it reveals data provider's real-time information. These problems can be solved by using a method of inserting dummy data. By using this method, a attacker cannot distinguish the original data from the transmitting data. In this paper, we propose a method for privacy preserving frequent itemset mining by using the technique of inserting dummy data. In addition, the proposed method is effective in terms of calculation because it does not require encryption technology or other mathematical operations.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.4
• /
• pp.53-62
• /
• 2010

In VANETs (Vehicular Ad hoc NETwork), conditional anonymity must be provided to protect privacy of vehicles while enabling authorities to identify misbehaving vehicles. To this end, previous systems provide a mechanism to revoke the anonymity of individual messages. In VANET, if we can trace the movement path of vehicles, it can be useful in determining the liability of vehicles in car accidents and crime investigations. Although route tracing can be provided using previous message revocation techniques, they violate privacy of other vehicles. In this paper, we provide a route tracing technique that protects privacy of vehicles that are not targeted. The proposed method can be employed independently of the authentication mechanism used and includes a mechanism to prevent authorities from abusing this new function.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.4
• /
• pp.7-17
• /
• 2019

Machine learning is one of the most accurate techniques to predict and analyze various phenomena. K-means clustering is a kind of machine learning technique that classifies given data into clusters of similar data. Because it is desirable to perform an analysis based on a lot of data for better performance, K-means clustering can be performed in a model with a server that calculates the centroids of the clusters, and a number of clients that provide data to server. However, this model has the problem that if the clients' data are associated with private information, the server can infringe clients' privacy. In this paper, to solve this problem in a model with a number of clients, we propose a privacy-preserving K-means clustering method that can perform machine learning, concealing private information using homomorphic encryption.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1904-1913
• /
• 2021

With the proliferation of smart phones and the development of IoT technology, it has become possible to collect personal data for public purposes. However, users are afraid of voluntarily providing their private data due to privacy issues. To remedy this problem, mainly three techniques have been studied: data disturbance, traditional encryption, and homomorphic encryption. In this work, we perform simulations to compare them in terms of accuracy, message length, and computation delay. Experiment results show that the data disturbance method is fast and inaccurate while the traditional encryption method is accurate and slow. Similar to traditional encryption algorithms, the homomorphic encryption algorithm is relatively effective in privacy preserving because it allows computing encrypted data without decryption, but it requires high computation costs as well. However, its main cost, arithmetic operations, can be processed in parallel. Also, data analysis using the homomorphic encryption needs to do decryption only once at any number of data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1799-1818
• /
• 2018

Malware detections continue to be a challenging task as attackers may be aware of the rules used in malware detection mechanisms and constantly generate new breeds of malware to evade the current malware detection mechanisms. Consequently, novel and innovated malware detection techniques need to be investigated to deal with this circumstance. In this paper, we propose a new secure malware detection system in which API call fragments are used to recognize potential malware instances, and these API call fragments together with the homomorphic encryption technique are used to construct a privacy-preserving Naive Bayes classifier (PP-NBC). Experimental results demonstrate that the proposed PP-NBC can successfully classify instances of malware with a hit-rate as high as 94.93%.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.924-926
• /
• 2021

AI (Artificial Intelligence) is being utilized in various fields and services to give convenience to human life. Unfortunately, there are many security vulnerabilities in today's ML (Machine Learning) systems, causing various privacy concerns as some AI models need individuals' private data to train them. Such concerns lead to the interest in ML systems which can preserve the privacy of individuals' data. This paper introduces the latest research on various attacks that infringe data privacy and the corresponding defense techniques.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.4 s.304
• /
• pp.25-32
• /
• 2005

The spread of mobile devices, PDAs and sensors has enabled the construction of ubiquitous computing environments, transforming regular physical spaces into 'Smart space' augmented with intelligence and enhanced with services. However, the deployment of this computing paradigm in real-life is disturbed by poor security, particularly, the lack of proper authentication and authorization techniques. Also, it is very important not only to find security measures but also to preserve user privacy in ubiquitous computing environments. In this Paper, we propose efficient user authentication and authorization model with anonymity for the privacy-preserving for ubiquitous computing environments. Our model is suitable for distributed environments with the computational constrained devices by using MAC-based anonymous certificate and security association token instead of using Public key encryption technique. And our Proposed Protocol is better than Kerberos system in sense of cryptographic computation processing.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1079-1090
• /
• 2014

Data mining is a technique to get the useful information that can be utilized for marketing and pattern analysis by processing the data that we have. However, when we use this technique, data provider's personal data can be leaked by accident. To protect these data from leakage, there were several techniques have been studied to preserve privacy. Vertically partitioned data is a state called that the data is separately provided to various number of user. On these vertically partitioned data, there was some methods developed to distinguishing kth element and (k+1) th element by using score. However, in previous method, we can only use on two-party case, so in this paper, we propose the extended technique by using paillier cryptosystem which can use on multi-party case.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.2
• /
• pp.347-355
• /
• 2012

A biometric hardware security module is a physical device that comes in the form of smartcard or some other USB type security token is composed with biometric sensor and microcontroller unit (MCU). These modules are designed to process key generation and electronic signature generation inside of the device (so that the security token can safely save and store confidential information, like the electronic signature generation key and the biometric sensing information). However, the existing model is not consistent that can be caused by the disclosure of an ID and password, which is used by the existing personal authentication technique based on the security token, and provide a high level of security and personal authentication techniques that can prevent any intentional misuse of a digital certificate. So, this paper presents a model that can provide high level of security by utilizing the biometric security token and Public Key Infrastructure efficiently, presenting a model for privacy preserving personal authentication that links the biometric security token and the digital certificate.