Enhancing Privacy in PUF-Cash through Multiple Trusted Third Parties and Reinforcement Learning

2022 ◽  
Vol 18 (1) ◽  
pp. 1-26
Author(s):  
Georgios Fragkos ◽  
Cyrus Minwalla ◽  
Eirini Eleni Tsiropoulou ◽  
Jim Plusquellic
Keyword(s):  
User Anonymity ◽  
Third Party ◽  
Security And Privacy ◽  
Machine Learning Techniques ◽  
User Privacy ◽  
Trusted Third Party ◽  
Physical Unclonable Functions ◽  
Learning Techniques ◽  
Direct Contrast ◽  
Debit Cards

Electronic cash ( e-Cash ) is a digital alternative to physical currency such as coins and bank notes. Suitably constructed, e-Cash has the ability to offer an anonymous offline experience much akin to cash, and in direct contrast to traditional forms of payment such as credit and debit cards. Implementing security and privacy within e-Cash, i.e., preserving user anonymity while preventing counterfeiting, fraud, and double spending, is a non-trivial challenge. In this article, we propose major improvements to an e-Cash protocol, termed PUF-Cash, based on physical unclonable functions ( PUFs ). PUF-Cash was created as an offline-first, secure e-Cash scheme that preserved user anonymity in payments. In addition, PUF-Cash supports remote payments; an improvement over traditional currency. In this work, a novel multi-trusted-third-party exchange scheme is introduced, which is responsible for “blinding” Alice’s e-Cash tokens; a feature at the heart of preserving her anonymity. The exchange operations are governed by machine learning techniques which are uniquely applied to optimize user privacy, while remaining resistant to identity-revealing attacks by adversaries and trusted authorities. Federation of the single trusted third party into multiple entities distributes the workload, thereby improving performance and resiliency within the e-Cash system architecture. Experimental results indicate that improvements to PUF-Cash enhance user privacy and scalability.

scholarly journals Decentralized Privacy-Preserving Data Aggregation Scheme for Smart Grid Based on Blockchain

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5282 ◽  
Author(s):  
Hongbin Fan ◽  
Yining Liu ◽  
Zhixin Zeng
Keyword(s):  
Smart Grid ◽  
Data Aggregation ◽  
Privacy Preserving ◽  
Third Party ◽  
Security And Privacy ◽  
Communication Overhead ◽  
User Privacy ◽  
Grid Data ◽  
Trusted Third Party ◽  
Grid Based

As a next-generation power system, the smart grid can implement fine-grained smart metering data collection to optimize energy utilization. Smart meters face serious security challenges, such as a trusted third party or a trusted authority being attacked, which leads to the disclosure of user privacy. Blockchain provides a viable solution that can use its key technologies to solve this problem. Blockchain is a new type of decentralized protocol that does not require a trusted third party or a central authority. Therefore, this paper proposes a decentralized privacy-preserving data aggregation (DPPDA) scheme for smart grid based on blockchain. In this scheme, the leader election algorithm is used to select a smart meter in the residential area as a mining node to build a block. The node adopts Paillier cryptosystem algorithm to aggregate the user’s power consumption data. Boneh-Lynn-Shacham short signature and SHA-256 function are applied to ensure the confidentiality and integrity of user data, which is convenient for billing and power regulation. The scheme protects user privacy data while achieving decentralization, without relying on TTP or CA. Security analysis shows that our scheme meets the security and privacy requirements of smart grid data aggregation. The experimental results show that this scheme is more efficient than existing competing schemes in terms of computation and communication overhead.

Permission-Based Malware Detection System for Android Using Machine Learning Techniques

2019 ◽  
Vol 29 (01) ◽  
pp. 43-61 ◽  
Author(s):  
Recep Sinan Arslan ◽  
İbrahim Alper Doğru ◽  
Necaattin Barişçi
Keyword(s):  
Machine Learning ◽  
Mobile Applications ◽  
Detection System ◽  
Security And Privacy ◽  
Machine Learning Techniques ◽  
Accuracy Rate ◽  
Code Analysis ◽  
Learning Techniques ◽  
Accuracy Level ◽  
Privacy Models

Mobile applications create their own security and privacy models through permission-based models. Some applications may request extra permissions that they do not need but may use for suspicious activities. The aim of this study is to identify those spare permissions requested and use this information in the security and privacy approach, which uses static and code analysis together and applies them to the existing datasets; then the results are compared and accuracy level is determined. Classification is made with an accuracy rate of 91.95%.

Anonymity Query Method of Outsourced Database

2013 ◽  
Vol 798-799 ◽  
pp. 837-841
Author(s):  
Yong Hua Zhang
Keyword(s):  
Privacy Protection ◽  
Third Party ◽  
User Privacy ◽  
Trusted Third Party ◽  
Outsourced Database ◽  
Access Model

This paper analyzes the traditional outsourcing model (TOM). Aiming at that TOM has disadvantages such as low security on User Privacy, this paper proposes a new access model in outsourced database. Using the trusted third party (TTP ) makes all operations in the database become anonymous in order to achieve the purpose of user privacy protection.

scholarly journals The Prediction of Application for Loan using Machine Learning Technique

2020 ◽  
Vol 9 (10) ◽  
pp. 265-268
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Predictive Performance ◽  
Third Party ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Internet Platform ◽  
The Many ◽  
Prediction Problems

Machine learning techniques are used to verify the many kinds of loan prediction problems. This study pursueS two major goals. Firstly, this paper is to understand the role of variables in loan prediction modeling better. Secondly, the study evaluates the predictive performance of the decision trees. The corresponding variable information is drawn from a third-party website, international challenge on the popular internet platform Kaggle (www.kaggle.com), which provides data in the title of ‘Loan Prediction’ that was uploaded by Amit Parajapet. We used decision tree which is a powerful and popular machine learning algorithm to this date for predicting and classifying big data. Based on these results, first, women seem to be more likely to get to loan than men. credit history, self-employed, property area, and applicant income also show significance with loan prediction. This study contributes to the literature regarding loan prediction by providing a global model summarizing the loan prediction determinants of customers’ factors.

scholarly journals XGB-RF: A Hybrid Machine Learning Approach for IoT Intrusion Detection

Telecom ◽  
2022 ◽  
Vol 3 (1) ◽  
pp. 52-69
Author(s):  
Jabed Al Faysal ◽  
Sk Tahmid Mostafa ◽  
Jannatul Sultana Tamanna ◽  
Khondoker Mirazul Mumenin ◽  
Md. Mashrur Arifin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Security And Privacy ◽  
Machine Learning Techniques ◽  
Gradient Boosting ◽  
Network Systems ◽  
Learning Techniques ◽  
Extreme Gradient Boosting ◽  
Hybrid Machine ◽  
Security Operations ◽  
Iot Devices

In the past few years, Internet of Things (IoT) devices have evolved faster and the use of these devices is exceedingly increasing to make our daily activities easier than ever. However, numerous security flaws persist on IoT devices due to the fact that the majority of them lack the memory and computing resources necessary for adequate security operations. As a result, IoT devices are affected by a variety of attacks. A single attack on network systems or devices can lead to significant damages in data security and privacy. However, machine-learning techniques can be applied to detect IoT attacks. In this paper, a hybrid machine learning scheme called XGB-RF is proposed for detecting intrusion attacks. The proposed hybrid method was applied to the N-BaIoT dataset containing hazardous botnet attacks. Random forest (RF) was used for the feature selection and eXtreme Gradient Boosting (XGB) classifier was used to detect different types of attacks on IoT environments. The performance of the proposed XGB-RF scheme is evaluated based on several evaluation metrics and demonstrates that the model successfully detects 99.94% of the attacks. After comparing it with state-of-the-art algorithms, our proposed model has achieved better performance for every metric. As the proposed scheme is capable of detecting botnet attacks effectively, it can significantly contribute to reducing the security concerns associated with IoT systems.

scholarly journals Categorization of CVE Based on Vulnerability Software By Using Machine Learning Techniques

2021 ◽  
Vol 10 (3) ◽  
pp. 2637-2644
Keyword(s):  
Daily Life ◽  
Reliable Data ◽  
Third Party ◽  
Machine Learning Techniques ◽  
Open Door ◽  
Major Goal ◽  
Huge Data ◽  
Learning Techniques ◽  
Vulnerability Testing

Public Platform is designed as an online website for researchers to collect reliable data for the study. NVD plays a significant role in analyzing The result of analysis in association influence metrics CVSS, type of CWE and applicability reports weakness CPE. The vulnerability testing is not performed by NVD while third-party security researchers and vulnerability controllers give information that has been assigned these attributes. ML plays a significant part in our daily life for the classification of huge data and is giving fruitful results. Because of that result, major steps have been made against criminal activities or unauthorized use of electronic data and protect the data from attackers. The major goal of this research is to categorize CVE Based Vulnerability Software throughout the last two years, 2019-2020.The findings of this study were used to ML for the categorization of CVE and compared and will open door for the fresh researchers and professionals.

Using machine learning techniques to reduce data annotation time

2006 ◽  
Author(s):  
Christopher Schreiner ◽  
Kari Torkkola ◽  
Mike Gardner ◽  
Keshu Zhang
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Data Annotation ◽  
Learning Techniques

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

Sign in / Sign up

Export Citation Format

Share Document