Xukai Zou

Permanent URI for this collection

https://hdl.handle.net/1805/26681

Creating Secure and Private-Preserving Cyber Infrastructure

The project is the first attempt to build a secure, holistic, and resilient cybersecurity architecture for any computing systems so that different types of users can remotely access and share protected data/resource/workflow in a free, flexible, yet finely-controlled, manner. The developed secure infrastructure will provide multi-level comprehensive protection from user authentication to fine-tuned data access, to confidentiality, integrity, availability, and traceability. The developed secure architecture is based on cutting-edge and advanced security technologies most of which have been invented or designed by Professor Zou and his team of researchers. The secure architecture can be applied to any multi-user and dynamic data/resource sharing systems and cyber infrastructures such as scientific infrastructures, health care systems, power-grid infrastructures, law-enforcement and forensic systems, and secure smart-city and smart-home infrastructures to protect the systems or infrastructures from both internal and external attacks.

Professor Zou's translation of research into secure, online transactions and interactions is another excellent example of how IUPUI's faculty members are TRANSLATING their RESEARCH INTO PRACTICE.

Browse

Now showing 1 - 10 of 14

A Cancellable and Privacy-Preserving Facial Biometric Authentication Scheme
(IEEE, 2017) Phillips, Tyler; Zou, Xukai; Li, Feng; Computer and Information Science, School of Science
In recent years, biometric, or "who you are," authentication has grown rapidly in acceptance and use. Biometric authentication offers users the convenience of not having to carry a password, PIN, smartcard, etc. Instead, users will use their inherent biometric traits for authentication and, as a result, risk their biometric information being stolen. The security of users' biometric information is of critical importance within a biometric authentication scheme as compromised data can reveal sensitive information: race, gender, illness, etc. A cancellable biometric scheme, the "BioCapsule" scheme, proposed by researchers from Indiana University Purdue University Indianapolis, aims to mask users' biometric information and preserve users' privacy. The BioCapsule scheme can be easily embedded into existing biometric authentication systems, and it has been shown to preserve user-privacy, be resistant to several types of attacks, and have minimal effects on biometric authentication system accuracy. In this research we present a facial authentication system which employs several cutting-edge techniques. We tested our proposed system on several face databases, both with and without the BioCapsule scheme being embedded into our system. By comparing our results, we quantify the effects the BioCapsule scheme, and its security benefits, have on the accuracy of our facial authentication system.
Design and Implementation of Privacy-Preserving, Flexible and Scalable Role-Based Hierarchical Access Control
(IEEE, 2019-12) Phillips, Tyler; Yu, Xiaoyuan; Haakenson, Brandon; Zou, Xukai; Computer and Information Science, School of Science
In many domains, organizations must model personnel and corresponding data access privileges as fine-grained hierarchical access control models. One class of such models, Role-based Access Control (RBAC) models, has been widely accepted and deployed. However, RBAC models are often used without involving cryptographic keys nor considering confidentiality/privacy at the data level. How to design, implement and dynamically modify such a hierarchy, ensure user and data privacy and distribute and manage necessary cryptographic keys are issues of the utmost importance. One elegant solution for cryptography-based hierarchical access control combines the collusion-resistant and privacy-preserving Access Control Polynomial (ACP) and Atallah's Dynamic and Efficient Extended Key Management scheme. Such a model involves cryptographic keys used to encrypt data, can address confidentiality/privacy at the data level and can efficiently support dynamic changes to the RBAC access hierarchy. In this paper, we discuss several implementation challenges and propose solutions when deploying such a system including: data encryption and decryption, key storage and key distribution. Furthermore, we provide analysis of the efficiency and scalability of the resulting system.
Electronic Voting Technology Inspired Interactive Teaching and Learning Pedagogy and Curriculum Development for Cybersecurity Education
(Springer, 2021-07) Hosler, Ryan; Zou, Xukai; Bishop, Matt; Computer and Information Science, School of Science
Cybersecurity is becoming increasingly important to individuals and society alike. However, due to its theoretical and practical complexity, keeping students interested in the foundations of cybersecurity is a challenge. One way to excite such interest is to tie it to current events, for example elections. Elections are important to both individuals and society, and typically dominate much of the news before and during the election. We are developing a curriculum based on elections and, in particular, an electronic voting protocol. Basing the curriculum on an electronic voting framework allows one to teach critical cybersecurity concepts such as authentication, privacy, secrecy, access control, encryption, and the role of non-technical factors such as policies and laws in cybersecurity, which must include societal and human factors. Student-centered interactions and projects allow them to apply the concepts, thereby reinforcing their learning.
Energy-Efficient Device Selection in Federated Edge Learning
(IEEE, 2021-07) Peng, Cheng; Hu, Qin; Chen, Jianan; Kang, Kyubyung; Li, Feng; Zou, Xukai; Computer and Information Science, School of Science
Due to the increasing demand from mobile devices for the real-time response of cloud computing services, federated edge learning (FEL) emerges as a new computing paradigm, which utilizes edge devices to achieve efficient machine learning while protecting their data privacy. Implementing efficient FEL suffers from the challenges of devices’ limited computing and communication resources, as well as unevenly distributed datasets, which inspires several existing research focusing on device selection to optimize time consumption and data diversity. However, these studies fail to consider the energy consumption of edge devices given their limited power supply, which can seriously affect the cost-efficiency of FEL with unexpected device dropouts. To fill this gap, we propose a device selection model capturing both energy consumption and data diversity optimization, under the constraints of time consumption and training data amount. Then we solve the optimization problem by reformulating the original model and designing a novel algorithm, named E2DS, to reduce the time complexity greatly. By comparing with two classical FEL schemes, we validate the superiority of our proposed device selection mechanism for FEL with extensive experimental results.
Enhancing Biometric-Capsule-based Authentication and Facial Recognition via Deep Learning
(ACM, 2019) Phillips, Tyler; Zou, Xukai; Li, Feng; Li, Ninghui; Computer and Information Science, School of Science
In recent years, developers have used the proliferation of biometric sensors in smart devices, along with recent advances in deep learning, to implement an array of biometrics-based authentication systems. Though these systems demonstrate remarkable performance and have seen wide acceptance, they present unique and pressing security and privacy concerns. One proposed method which addresses these concerns is the elegant, fusion-based BioCapsule method. The BioCapsule method is provably secure, privacy-preserving, cancellable and flexible in its secure feature fusion design. In this work, we extend BioCapsule to face-based recognition. Moreover, we incorporate state-of-art deep learning techniques into a BioCapsule-based facial authentication system to further enhance secure recognition accuracy. We compare the performance of an underlying recognition system to the performance of the BioCapsule-embedded system in order to demonstrate the minimal effects of the BioCapsule scheme on underlying system performance. We also demonstrate that the BioCapsule scheme outperforms or performs as well as many other proposed secure biometric techniques.
Hardware Speculation Vulnerabilities and Mitigations
(IEEE, 2021-10) Swearingen, Nathan; Hosler, Ryan; Zou, Xukai; Computer and Information Science, School of Science
This paper will discuss speculation vulnerabilities, which arise from hardware speculation, an optimization technique. Unlike many other types of vulnerabilities, these are very difficult to patch completely, and there are techniques developed to mitigate them. We will look at many of the variants of this type of vulnerability. We will look at the techniques mitigating those vulnerabilities and the effectiveness and scope of each. Finally, we will compare and evaluate different vulnerabilities and mitigation techniques and recommend how various mitigation techniques apply to different situations.
Koinonia: verifiable e-voting with long-term privacy
(ACM, 2019) Ge, Huangyi; Chau, Sze Yiu; Gonsalves, Victor E.; Liu, Huian; Wang, Tianhao; Zou, Xukai; Li, Ninghui; Computer and Information Science, School of Science
Despite years of research, many existing e-voting systems do not adequately protect voting privacy. In most cases, such systems only achieve "immediate privacy", that is, they only protect voting privacy against today's adversaries, but not against a future adversary, who may possess better attack technologies like new cryptanalysis algorithms and/or quantum computers. Previous attempts at providing long-term voting privacy (dubbed "everlasting privacy" in the literature) often require additional trusts in parties that do not need to be trusted for immediate privacy. In this paper, we present a framework of adversary models regarding e-voting systems, and analyze possible threats to voting privacy under each model. Based on our analysis, we argue that secret-sharing based voting protocols offer a more natural and elegant privacy-preserving solution than their encryption-based counterparts. We thus design and implement Koinonia, a voting system that provides long-term privacy against powerful adversaries and enables anyone to verify that each ballot is well-formed and the tallying is done correctly. Our experiments show that Koinonia protects voting privacy with a reasonable performance.
Learning Discriminative Features for Adversarial Robustness
(IEEE Xplore, 2022-04) Hosler, Ryan; Phillips, Tyler; Yu, Xiaoyuan; Sundar, Agnideven; Zou, Xukai; Li, Feng; Computer and Information Science, School of Science
Deep Learning models have shown incredible image classification capabilities that extend beyond humans. However, they remain susceptible to image perturbations that a human could not perceive. A slightly modified input, known as an Adversarial Example, will result in drastically different model behavior. The use of Adversarial Machine Learning to generate Adversarial Examples remains a security threat in the field of Deep Learning. Hence, defending against such attacks is a studied field of Deep Learning Security. In this paper, we present the Adversarial Robustness of discriminative loss functions. Such loss functions specialize in either inter-class or intra-class compactness. Therefore, generating an Adversarial Example should be more difficult since the decision barrier between different classes will be more significant. We conducted White-Box and Black-Box attacks on Deep Learning models trained with different discriminative loss functions to test this. Moreover, each discriminative loss function will be optimized with and without Adversarial Robustness in mind. From our experimentation, we found White-Box attacks to be effective against all models, even those trained for Adversarial Robustness, with varying degrees of effectiveness. However, state-of-the-art Deep Learning models, such as Arcface, will show significant Adversarial Robustness against Black-Box attacks while paired with adversarial defense methods. Moreover, by exploring Black-Box attacks, we demonstrate the transferability of Adversarial Examples while using surrogate models optimized with different discriminative loss functions.
Multi-Armed-Bandit-based Shilling Attack on Collaborative Filtering Recommender Systems
(IEEE, 2020-12) Palanisamy Sundar, Agnideven; Li, Feng; Zou, Xukai; Hu, Qin; Gao, Tianchong; Computer and Information Science, School of Science
Collaborative Filtering (CF) is a popular recommendation system that makes recommendations based on similar users' preferences. Though it is widely used, CF is prone to Shilling/Profile Injection attacks, where fake profiles are injected into the CF system to alter its outcome. Most of the existing shilling attacks do not work on online systems and cannot be efficiently implemented in real-world applications. In this paper, we introduce an efficient Multi-Armed-Bandit-based reinforcement learning method to practically execute online shilling attacks. Our method works by reducing the uncertainty associated with the item selection process and finds the most optimal items to enhance attack reach. Such practical online attacks open new avenues for research in building more robust recommender systems. We treat the recommender system as a black box, making our method effective irrespective of the type of CF used. Finally, we also experimentally test our approach against popular state-of-the-art shilling attacks.
A New Look at Old Abe’s Color Guard
(Coddington, 2019) Phillips, Tyler; Zou, Xukai; Byrd, Kenneth E.; Computer and Information Science, School of Science
Many images of the American Civil War exist today and allow us to gain insight into the lives’ of those involved in the conflict. Unfortunately, these images also pose questions as many of the soldiers they depict are unidentified or identified with unknown reliability. One such image is that of the Wisconsin Infantry Color Guard and their bald eagle mascot “Old Abe.” One of the men in the color guard has been identified as George W. Riley due to an inscription on the back of the image. We perform state-of-art biometric-facial analysis of this soldier and several candidate identities. Through this biometric analysis and corroborating historical documents, we present compelling evidence that this soldier is not George W. Riley, but is more likely Walter J. Quick.

Browse

Browsing Xukai Zou by Author "Computer and Information Science, School of Science"

Results Per Page

Sort Options