Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Artificial Intelligence and Robotics (34)
- Business (33)
- Social and Behavioral Sciences (33)
- Engineering (29)
- Databases and Information Systems (26)
-
- Technology and Innovation (24)
- Management Information Systems (23)
- Cybersecurity (22)
- Software Engineering (18)
- Education (17)
- Public Affairs, Public Policy and Public Administration (16)
- Computer Engineering (15)
- Other Computer Sciences (15)
- OS and Networks (14)
- Theory and Algorithms (14)
- Data Science (13)
- Sociology (12)
- Systems Architecture (12)
- Defense and Security Studies (9)
- Electrical and Computer Engineering (9)
- Science and Technology Policy (9)
- Criminology (8)
- Criminology and Criminal Justice (7)
- Legal Studies (7)
- Medicine and Health Sciences (7)
- Forensic Science and Technology (6)
- Graphics and Human Computer Interfaces (6)
- Institution
-
- Singapore Management University (66)
- Old Dominion University (34)
- Kennesaw State University (25)
- Edith Cowan University (24)
- United Arab Emirates University (18)
-
- Chinese Academy of Sciences (9)
- Bridgewater State University (7)
- California State University, San Bernardino (6)
- Dakota State University (6)
- University of South Alabama (5)
- Dartmouth College (3)
- Portland State University (3)
- University at Albany, State University of New York (3)
- University of Arkansas, Fayetteville (3)
- University of Central Florida (3)
- Wayne State University (3)
- Arkansas Tech University (2)
- Clemson University (2)
- Indiana State University (2)
- Louisiana State University (2)
- Loyola University Chicago (2)
- Michigan Technological University (2)
- University of Arkansas Little Rock (2)
- University of Denver (2)
- University of Texas Rio Grande Valley (2)
- University of Texas at Arlington (2)
- Air Force Institute of Technology (1)
- American University in Cairo (1)
- Association of Arab Universities (1)
- California Polytechnic State University, San Luis Obispo (1)
- Keyword
-
- Cybersecurity (34)
- Security (18)
- Privacy (14)
- Blockchain (13)
- Machine learning (11)
-
- Artificial intelligence (8)
- Internet of Things (6)
- Protocols (6)
- Cybercrime (5)
- Data privacy (5)
- Data security (5)
- Federated learning (5)
- Internet of things (5)
- Servers (5)
- Training (5)
- Anomaly detection (4)
- Computer security (4)
- Cryptography (4)
- Deep Learning (4)
- Education (4)
- Encryption (4)
- Homomorphic encryption (4)
- Intrusion detection (4)
- Intrusion detection system (4)
- IoT (4)
- Natural language processing (4)
- Adaptation models (3)
- Bitcoin (3)
- Classification (3)
- Cyber security (3)
- Publication
-
- Research Collection School Of Computing and Information Systems (62)
- Research outputs 2022 to 2026 (23)
- Journal of Cybersecurity Education, Research and Practice (18)
- Cybersecurity Undergraduate Research Showcase (10)
- Bulletin of Chinese Academy of Sciences (Chinese Version) (9)
-
- Theses (8)
- International Journal of Cybersecurity Intelligence & Cybercrime (7)
- Thesis/ Dissertation Defenses (7)
- Electronic Theses, Projects, and Dissertations (6)
- Research & Publications (6)
- KSU Proceedings on Cybersecurity Education, Research and Practice (5)
- School of Cybersecurity Faculty Publications (5)
- VMASC Publications (5)
- Dissertations (4)
- Electrical & Computer Engineering Faculty Publications (4)
- Theses and Dissertations (4)
- Chemical Engineering and Materials Science Faculty Research Publications (3)
- Computer Science and Computer Engineering Undergraduate Honors Theses (3)
- Electronic Theses and Dissertations (3)
- Graduate Theses and Dissertations (2019 - present) (3)
- Graduate Thesis and Dissertation 2023-2024 (3)
- Information Technology & Decision Sciences Faculty Publications (3)
- Student Research Symposium (3)
- ALL - Honors Theses (2)
- ATU Scholars Symposium (2)
- African Conference on Information Systems and Technology (2)
- Computer Science Senior Theses (2)
- Computer Science and Engineering Dissertations - Archive (2)
- Computer Science: Faculty Publications and Other Works (2)
- Dissertations and Theses Collection (Open Access) (2)
- Publication Type
Articles 61 - 90 of 265
Full-Text Articles in Information Security
Understanding The Use Of Artificial Intelligence In Cybercrime, Sinyong Choi, Thomas Dearden, Katalin Parti
Understanding The Use Of Artificial Intelligence In Cybercrime, Sinyong Choi, Thomas Dearden, Katalin Parti
International Journal of Cybersecurity Intelligence & Cybercrime
Artificial intelligence is one of the newest innovations that offenders also exploit to satisfy their criminal desires. Although understanding cybercrimes associated with this relatively new technology is essential in developing proper preventive measures, little has been done to examine this area. Therefore, this paper provides an overview of the articles featured in the special issue of the International Journal of Cybersecurity Intelligence and Cybercrime, ranging from deepfake in the metaverse to social engineering attacks. This issue includes articles that were presented by the winners of the student paper competition at the 2024 International White Hat Conference.
Investigating The Intersection Of Ai And Cybercrime: Risks, Trends, And Countermeasures, Sanaika Shetty, Kyung-Shick Choi, Insun Park
Investigating The Intersection Of Ai And Cybercrime: Risks, Trends, And Countermeasures, Sanaika Shetty, Kyung-Shick Choi, Insun Park
International Journal of Cybersecurity Intelligence & Cybercrime
No abstract provided.
Integrated Model Of Cybercrime Dynamics: A Comprehensive Framework For Understanding Offending And Victimization In The Digital Realm, Troy Smith Phd
Integrated Model Of Cybercrime Dynamics: A Comprehensive Framework For Understanding Offending And Victimization In The Digital Realm, Troy Smith Phd
International Journal of Cybersecurity Intelligence & Cybercrime
This article introduces the Integrated Model of Cybercrime Dynamics (IMCD), a novel theoretical framework for examining the complex interplay between individual characteristics, online behavior, environmental factors, and outcomes related to cybercrime offending and victimization. The model incorporates key concepts from existing theories, empirical evidence, and interdisciplinary perspectives to provide a comprehensive framework. In contrast to traditional criminological theories, the proposed model integrates concepts from multiple disciplines to offer a holistic framework that captures the complexity of cybercrime and specifically caters for the uniqueness of cyberspace. The article will provide a detailed overview of the conceptual model, its theoretical underpinnings drawing …
Use Your Own Device (Uyod): Framework For Building A Human Firewall, Tapiwa Gundu, Kevin Kativu
Use Your Own Device (Uyod): Framework For Building A Human Firewall, Tapiwa Gundu, Kevin Kativu
African Conference on Information Systems and Technology
The Use Your Own Device (UYOD) paradigm is increasingly common in modern digital workplaces, offering benefits like flexibility and cost savings but also introducing significant cybersecurity risks. This study develops a comprehensive framework for constructing a robust human firewall aimed at mitigating these risks. The research employs a systematic literature review (SLR) methodology, starting with a corpus of 198 articles, from which 17 high-quality studies were selected for in-depth analysis. Key components identified include cybersecurity awareness training, regular simulated attacks, clear policies and procedures, technology competence training, and fostering a security-first culture. Findings reveal that integrating these components into an …
Data Breach Mitigation In Hospital Database Management Systems – The Case Of A Hospital In South-South Nigeria, Leton Rebecca Nsereka, Irene Govender
Data Breach Mitigation In Hospital Database Management Systems – The Case Of A Hospital In South-South Nigeria, Leton Rebecca Nsereka, Irene Govender
African Conference on Information Systems and Technology
The damaging effects of data breaches result in the loss of sensitive data, operational downtime, financial losses, and, in extreme cases, legal action. This study investigates the Hospital Database Management systems (HDMS) in a selected hospital in South-South Nigeria for the mitigation of data breaches. The deployment of an Incident Response Framework for data breach mitigation on HDMS has yet to be fully researched, creating a gap literature. The research objectives were accomplished through mixed methods and design science research (DSR). About 180 participants including forty employees from the medical records unit and 140 patients/patient relatives, who interact with the …
Designing Cybersecurity Escape Rooms: A Gamified Approach To Undergraduate Learning, Thitima Srivatanakul
Designing Cybersecurity Escape Rooms: A Gamified Approach To Undergraduate Learning, Thitima Srivatanakul
Journal of Cybersecurity Education, Research and Practice
Gamification, including game-based learning (GBL), is a widely recognized pedagogical approach used for imparting and reinforcing cybersecurity knowledge and skills to learners. One innovative form of GBL gaining popularity across various educational levels, from secondary schools to professional development, is escape room-style education. This study is centered on the development and design of escape room activities tailored for teaching cybersecurity concepts, with a particular focus on web and software security, to undergraduate students at York College. The primary objectives of this research are twofold: firstly, to evaluate the effectiveness of educational escape room activities in reinforcing cybersecurity concepts taught in …
Cyberattack Detection And Handling For Neural Network-Approximated Economic Model Predictive Control, Jihan Abou Halloun, Helen E. Durand
Cyberattack Detection And Handling For Neural Network-Approximated Economic Model Predictive Control, Jihan Abou Halloun, Helen E. Durand
Chemical Engineering and Materials Science Faculty Research Publications
Cyberattacks on control systems can create unprofitable and unsafe operating conditions. To enhance safety and attack resiliency of control systems, cyberattack detection strategies can be developed. Prior work in our group has sought to develop cyberattack detection strategies that are integrated with an advanced control formulation known as Lyapunov-based economic model predictive control (LEMPC), in the sense that the controller properties can be used to analyze closed-loop stability in the presence or absence of undetected attacks. In this work, we consider neural network-approximated control laws, concepts for mitigating cyberattacks on such control laws, and how these ideas elucidate concepts in …
Lyapunov-Based Cyberattack Detection For Distinguishing Between Sensor And Actuator Attacks, Dominic Messina, Helen E. Durand
Lyapunov-Based Cyberattack Detection For Distinguishing Between Sensor And Actuator Attacks, Dominic Messina, Helen E. Durand
Chemical Engineering and Materials Science Faculty Research Publications
Control-theoretic cyberattack detection strategies are control strategies where control theory can be used in the design of the detection policies and analysis of stability properties with and without cyberattacks. This work provides a step toward understanding how to diagnose cyberattacks using control-theoretic cyberattack detection mechanisms. Specifically, we analyze the conditions under which a control-theoretic cyberattack detection strategy developed in our prior work to handle detection of simultaneous actuator and sensor attacks can be extended to distinguish between whether attacks are occurring on sensors or actuators. We present and evaluate heuristic concepts for attempting to diagnose sensor attacks; these again demonstrate …
Profit Considerations For Nonlinear Control-Integrated Cyberattack Detection On Process Actuators, Keshav Kasturi Rangan, Helen E. Durand
Profit Considerations For Nonlinear Control-Integrated Cyberattack Detection On Process Actuators, Keshav Kasturi Rangan, Helen E. Durand
Chemical Engineering and Materials Science Faculty Research Publications
Prior research from our group developed a control-integrated active actuator cyberattack detection strategy. This strategy continuously probed for cyberattacks by updating target steady-states at every sampling time and then moving the process state toward these over the subsequent sampling period. Attacks were fagged if a Lyapunov function around the target steady-state did not decrease over a sampling period. This strategy had the benefit of ensuring safety of the process until an attack was detected. However, the continuous probing for attacks could decrease profit from the process compared to not probing for the attacks, which could limit the attractiveness of the …
Detecting Anomalies In Blockchain Transactions Using Machine Learning Classifiers And Explainability Analysis, Mohammad Hasan, Mohammad Shahriar Rahman, Helge Janicke, Iqbal H. Sarker
Detecting Anomalies In Blockchain Transactions Using Machine Learning Classifiers And Explainability Analysis, Mohammad Hasan, Mohammad Shahriar Rahman, Helge Janicke, Iqbal H. Sarker
Research outputs 2022 to 2026
As the use of blockchain for digital payments continues to rise, it becomes susceptible to various malicious attacks. Successfully detecting anomalies within blockchain transactions is essential for bolstering trust in digital payments. However, the task of anomaly detection in blockchain transaction data is challenging due to the infrequent occurrence of illicit transactions. Although several studies have been conducted in the field, a limitation persists: the lack of explanations for the model's predictions. This study seeks to overcome this limitation by integrating explainable artificial intelligence (XAI) techniques and anomaly rules into tree-based ensemble classifiers for detecting anomalous Bitcoin transactions. The shapley …
Pias: Privacy-Preserving Incentive Announcement System Based On Blockchain For Internet Of Vehicles, Yonghua Zhan, Yang Yang, Hongju Cheng, Xiangyang Luo, Zhuangshuang Guan, Robert H. Deng
Pias: Privacy-Preserving Incentive Announcement System Based On Blockchain For Internet Of Vehicles, Yonghua Zhan, Yang Yang, Hongju Cheng, Xiangyang Luo, Zhuangshuang Guan, Robert H. Deng
Research Collection School Of Computing and Information Systems
More vehicles are connecting to the Internet of Things (IoT), transforming Vehicle Ad hoc Networks (VANETs) into the Internet of Vehicles (IoV), providing a more environmentally friendly and safer driving experience. Vehicular announcement networks show promise in vehicular communication applications. However, two major issues arise when establishing such a system. Firstly, user privacy cannot be guaranteed when messages are forwarded anonymously, thus the reliability of these messages is in question. Secondly, users often lack interest in responding to announcements. To address these problems, we introduce a Blockchain-based incentive announcement system called PIAS. This system enables anonymous message commitment in a …
Fdi : Attack Neural Code Generation Systems Through User Feedback Channel, Zhensu Sun, Xiaoning Du, Xiapu Luo, Fu Song, David Lo, Li Li
Fdi : Attack Neural Code Generation Systems Through User Feedback Channel, Zhensu Sun, Xiaoning Du, Xiapu Luo, Fu Song, David Lo, Li Li
Research Collection School Of Computing and Information Systems
Neural code generation systems have recently attracted increasing attention to improve developer productivity and speed up software development. Typically, these systems maintain a pre-trained neural model and make it available to general users as a service (e.g., through remote APIs) and incorporate a feedback mechanism to extensively collect and utilize the users' reaction to the generated code, i.e., user feedback. However, the security implications of such feedback have not yet been explored. With a systematic study of current feedback mechanisms, we find that feedback makes these systems vulnerable to feedback data injection (FDI) attacks. We discuss the methodology of FDI …
The Impact Of Managerial Myopia On Cybersecurity: Evidence From Data Breaches, Wen Chen, Xing Li, Haibin Wu, Liandong Zhang
The Impact Of Managerial Myopia On Cybersecurity: Evidence From Data Breaches, Wen Chen, Xing Li, Haibin Wu, Liandong Zhang
Research Collection School Of Accountancy
Using a sample of U.S. firms for the period 2005–2017, we provide evidence that managerial myopic actions contribute to corporate cybersecurity risk. Specifically, we show that abnormal cuts in discretionary expenditures, our proxy for managerial myopia, are positively associated with the likelihood of data breaches. The association is largely driven by firms that appear to cut discretionary expenditures to meet short-term earnings targets. In addition, the association is stronger for firms with greater short-term equity incentives, higher earnings response coefficients, low levels of institutional block ownership, or large market shares. Finally, firms appear to increase discretionary expenditures upon the announcement …
Efficient And Secure Federated Learning Against Backdoor Attacks, Yinbin Miao, Rongpeng Xie, Xinghua Li, Zhiquan Liu, Kim-Kwang Raymond Choo, Robert H. Deng
Efficient And Secure Federated Learning Against Backdoor Attacks, Yinbin Miao, Rongpeng Xie, Xinghua Li, Zhiquan Liu, Kim-Kwang Raymond Choo, Robert H. Deng
Research Collection School Of Computing and Information Systems
Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differential Privacy (LDP) solutions can provide privacy protection to a certain extent, but these solutions still cannot achieve adaptive perturbation in DNN model. In addition, this kind of schemes cause high communication overheads due to the curse of dimensionality of DNN, and are naturally vulnerable to backdoor attacks due to the inherent distributed characteristic. To solve these issues, …
Meta-Learning For Multi-Family Android Malware Classification, Yao Li, Dawei Yuan, Tao Zhang, Haipeng Cai, David Lo, Cuiyun Gao, Xiapu Luo, He Jiang
Meta-Learning For Multi-Family Android Malware Classification, Yao Li, Dawei Yuan, Tao Zhang, Haipeng Cai, David Lo, Cuiyun Gao, Xiapu Luo, He Jiang
Research Collection School Of Computing and Information Systems
With the emergence of smartphones, Android has become a widely used mobile operating system. However, it is vulnerable when encountering various types of attacks. Every day, new malware threatens the security of users' devices and private data. Many methods have been proposed to classify malicious applications, utilizing static or dynamic analysis for classification. However, previous methods still suffer from unsatisfactory performance due to two challenges. First, they are unable to address the imbalanced data distribution problem, leading to poor performance for malware families with few members. Second, they are unable to address the zero-day malware (zero-day malware refers to malicious …
Real Time Pii Scanning, John David
Real Time Pii Scanning, John David
Electronic Theses and Dissertations
The increased amount of web applications and internet software solutions utilizing cloud frameworks has contributed to large data sets of system log messages being generated constantly. These messages may contain sensitive data, creating an additional security risk for the systems and contributing to the need for analysis of such large volumes of data in real time. Large commercial data monitoring systems can solve for these analysis requirements, but they can be costly. We present a solution to analyzing web application log data which ingests it, processes it and visualizes sensitive data found within in real time. Our solution utilizes an …
The Impact Of Model Variations On The Robustness Of Deep Learning Models In Adversarial Settings, Firuz Juraev, Mohammed Abuhamad, Simon S. Woo, George K. Thiruvathukal, Tamer Abuhmed
The Impact Of Model Variations On The Robustness Of Deep Learning Models In Adversarial Settings, Firuz Juraev, Mohammed Abuhamad, Simon S. Woo, George K. Thiruvathukal, Tamer Abuhmed
Computer Science: Faculty Publications and Other Works
Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include applying variations of sophisticated techniques that improve the performance of models. However, such models are not immune to adversarial manipulations, which can cause the system to misbehave and remain unnoticed by experts. The frequency of modifications to existing deep learning models necessitates thorough analysis to determine the impact on models’ robustness. In this work, we present an experimental evaluation of the effects of model modifications on deep learning model robustness using …
Concept And Development Trend Of Novel E-Infrastructure Platform, Jing Xu, Chuan Tang, Kuangjunyu Yang, Juan Zhang, Ru Huang
Concept And Development Trend Of Novel E-Infrastructure Platform, Jing Xu, Chuan Tang, Kuangjunyu Yang, Juan Zhang, Ru Huang
Bulletin of Chinese Academy of Sciences (Chinese Version)
E-infrastructure platform has become a critical strategic asset for driving national scientific and technological innovation, and is the focus of strategic deployment by technologically advanced countries globally. This study, through the analysis of relevant strategy documents in the United States, European Union, and the United Kingdom, the relevant concepts and development changes of the novel E-infrastructure platform have been clarified. It also summarizes the planning process and development stages of e-infrastructure platform in the United States, Europe, and the United Kingdom, and analyzes that e-infrastructure platform will develop towards a new type of ecological, intelligent, diversified, and full process novel …
Exploring The Integration Of Blockchain In Iot Use Cases: Challenges And Opportunities, Ivannah George
Exploring The Integration Of Blockchain In Iot Use Cases: Challenges And Opportunities, Ivannah George
Electronic Theses, Projects, and Dissertations
Blockchain and The Internet of Things (IoT) is a significant paradigm which has gained traction in today’s digital age as two complimentary technologies. The combination of IoT's connectivity with blockchain's security creates new opportunities and solves problems associated with centralized systems. This culminating project aims to delve deeper into the integration of blockchain technology in IoT applications based on select use cases to uncover potential benefits and significant challenges of blockchain integration across different sectors. The research objectives to be addressed are: (RO1) How emerging vulnerabilities manifest in the implementation of blockchain within current IoT ecosystems. (RO2) How current opportunities …
Ensuring The Privacy Compliance Of Voice Personal Assistant Applications, Song Liao
Ensuring The Privacy Compliance Of Voice Personal Assistant Applications, Song Liao
All Dissertations
Voice Personal Assistants (VPA) such as Amazon Alexa and Google Assistant are quickly and seamlessly integrating into people’s daily lives. Meanwhile, the increased reliance on VPA services raises privacy concerns, such as the leakage of private conversations and sensitive information. Privacy policies play an important role in addressing users’ privacy concerns and developers are required to provide privacy policies to disclose their apps’ data practices. In addition, voice apps targeting users in European countries are required to comply with the GDPR (General Data Protection Regulation). However, little is known about whether these privacy policies are informative and trustworthy on emerging …
Anopay: Anonymous Payment For Vehicle Parking With Updatable Credential, Yang Yang, Wenyi Xue, Yonghua Zhan, Minming Huang, Yingjiu Li, Robert H. Deng
Anopay: Anonymous Payment For Vehicle Parking With Updatable Credential, Yang Yang, Wenyi Xue, Yonghua Zhan, Minming Huang, Yingjiu Li, Robert H. Deng
Research Collection School Of Computing and Information Systems
Many existing anonymous parking payment schemes lack high efficiency and flexibility. For instance, the calculation and communication costs involved in payment may linearly increase with the payment amount. In this paper, we propose an anonymous payment system (dubbed AnoPay) for vehicle parking, which leverages updatable attribute-based anonymous credentials and efficient zero-knowledge proof (ZKP) to achieve user anonymity and constant overhead for parking fee payment. To further improve the efficiency, we design a secure parking fee aggregation protocol based on linear homomorphic encryption to aggregate parking transactions, where the amount of each parking transaction is hidden and the privacy of the …
Simc 2.0: Improved Secure Ml Inference Against Malicious Clients, Guowen Xu, Xingshuo Han, Tianwei Zhang, Shengmin Xu, Jianting Ning, Xinyi Huang, Hongwei Li, Deng, Robert H.
Simc 2.0: Improved Secure Ml Inference Against Malicious Clients, Guowen Xu, Xingshuo Han, Tianwei Zhang, Shengmin Xu, Jianting Ning, Xinyi Huang, Hongwei Li, Deng, Robert H.
Research Collection School Of Computing and Information Systems
In this paper, we study the problem of secure ML inference against a malicious client and a semi-trusted server such that the client only learns the inference output while the server learns nothing. This problem is first formulated by Lehmkuhl et al. with a solution (MUSE, Usenix Security’21), whose performance is then substantially improved by Chandran et al.'s work (SIMC, USENIX Security’22). However, there still exists a nontrivial gap in these efforts towards practicality, giving the challenges of overhead reduction and secure inference acceleration in an all-round way. Based on this, we propose SIMC 2.0, which complies with the underlying …
Anopas: Practical Anonymous Transit Pass From Group Signatures With Time-Bound Keys, Rui Shi, Yang Yang, Yingjiu Li, Huamin Feng, Hwee Hwa Pang, Robert H. Deng
Anopas: Practical Anonymous Transit Pass From Group Signatures With Time-Bound Keys, Rui Shi, Yang Yang, Yingjiu Li, Huamin Feng, Hwee Hwa Pang, Robert H. Deng
Research Collection School Of Computing and Information Systems
An anonymous transit pass system allows passengers to access transport services within fixed time periods, with their privileges automatically deactivating upon time expiration. Although existing transit pass systems are deployable on powerful devices like PCs, their adaptation to more user-friendly devices, such as mobile phones with smart cards, is inefficient due to their reliance on heavy-weight operations like bilinear maps. In this paper, we introduce an innovative anonymous transit pass system, dubbed Anopas, optimized for deployment on mobile phones with smart cards, where the smart card is responsible for crucial lightweight operations and the mobile phone handles key-independent and time-consuming …
An Llm-Assisted Easy-To-Trigger Poisoning Attack On Code Completion Models: Injecting Disguised Vulnerabilities Against Strong Detection, Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, Yuan Hong
An Llm-Assisted Easy-To-Trigger Poisoning Attack On Code Completion Models: Injecting Disguised Vulnerabilities Against Strong Detection, Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, Yuan Hong
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To address this critical security challenge, we introduce CODEBREAKER, a pioneering LLM-assisted backdoor attack framework on code completion models. Unlike recent attacks that embed malicious payloads in detectable or irrelevant sections of the code (e.g., comments), CODEBREAKER leverages LLMs (e.g., GPT-4) for sophisticated payload transformation (without affecting functionalities), ensuring that both the poisoned data for fine-tuning and generated code can evade strong …
G2face: High-Fidelity Reversible Face Anonymization Via Generative And Geometric Priors, Haoxin Yang, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Jing Qin, Yi Wang, Pheng-Ann Heng, Shengfeng He
G2face: High-Fidelity Reversible Face Anonymization Via Generative And Geometric Priors, Haoxin Yang, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Jing Qin, Yi Wang, Pheng-Ann Heng, Shengfeng He
Research Collection School Of Computing and Information Systems
Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as encoder-decoder networks, often result in significant loss of facial details due to their limited learning capacity. Additionally, relying on latent manipulation in pre-trained GANs can lead to changes in ID-irrelevant attributes, adversely affecting data utility due to GAN inversion inaccuracies. This paper introduces G 2 Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data utility. We utilize a 3D face …
Peep With A Mirror: Breaking The Integrity Of Android App Sandboxing Via Unprivileged Cache Side Channel, Yan Lin, Joshua Wong, Xiang Li, Haoyu Ma, Debin Gao
Peep With A Mirror: Breaking The Integrity Of Android App Sandboxing Via Unprivileged Cache Side Channel, Yan Lin, Joshua Wong, Xiang Li, Haoyu Ma, Debin Gao
Research Collection School Of Computing and Information Systems
Application sandboxing is a well-established security principle employed in the Android platform to safeguard sensitive information. However, hardware resources, specifically the CPU caches, are beyond the protection of this software-based mechanism, leaving room for potential side-channel attacks. Existing attacks against this particular weakness of app sandboxing mainly target shared components among apps, hence can only observe system-level program dynamics (such as UI tracing). In this work, we advance cache side-channel attacks by demonstrating the viability of non-intrusive and fine-grained probing across different app sandboxes, which have the potential to uncover app-specific and private program behaviors, thereby highlighting the importance of …
Enhancing Cybersecurity For Unmanned Systems: A Comprehensive Literature Review, Jonathan Gabriel Mardoyan
Enhancing Cybersecurity For Unmanned Systems: A Comprehensive Literature Review, Jonathan Gabriel Mardoyan
Electronic Theses, Projects, and Dissertations
This culminating experience project addresses the pressing cybersecurity challenges encountered by unmanned autonomous vehicles. The research provides a comprehensive literature review on how hybrid encryption techniques can improve the security of its communication systems. The chosen research questions guiding this study are: (Q1) How can we enhance cybersecurity measures to safeguard the communication and transmission of sensitive data from unmanned systems, thereby preventing unauthorized access by malicious actors? (Q2) How can we ensure the confidentiality and integrity of messages exchanged with unmanned systems to a command-and-control center operating on the tactical edge? (Q3) How can hybrid encryption tackle the consumption …
Advancing Telehealth Through Artificial Intelligence: Incorporating Emotional Intelligence And Addressing Cybersecurity Challenges, Mahima Rajendra Pulgaonkar
Advancing Telehealth Through Artificial Intelligence: Incorporating Emotional Intelligence And Addressing Cybersecurity Challenges, Mahima Rajendra Pulgaonkar
Electronic Theses, Projects, and Dissertations
This culminating experience project explores the integration of Emotional Artificial Intelligence (Emotional AI) into telehealth systems, addressing the dual challenges of enhancing patient care and mitigating cybersecurity risks. The research questions are: (Q1) How can Emotionally Intelligent AI improve telehealth systems' ability to recognize and respond to mental health symptoms? and (Q2) What are the specific cybersecurity challenges associated with AI in telehealth and how can they be mitigated? The findings for each question are: Q1: Emotionally Intelligent AI can significantly enhance telehealth by providing personalized, empathetic interactions that improve patient engagement, adherence to treatment plans, and early detection of …
Increasing The Robustness Of Machine Learning By Adversarial Attacks, Gourab Mukhopadhyay
Increasing The Robustness Of Machine Learning By Adversarial Attacks, Gourab Mukhopadhyay
Theses and Dissertations
By perturbation or physical attacks any machine can be fooled into predicting something else other than the intended output. There are training data based on which the model is trained to predict unknown things. The objective was to create noises and shades of different levels on the images and do experiments for measuring accuracy and making the model classify the traffic signs. When it comes to adding shades to the pictures, pixels were modified for three different layers of the pictures. The experiment also shows that with the shadows getting deeper, the accuracies drop significantly. Here, some changes in pixels …
Survey Of Space Professionals’ Perception Of Satellite Cybersecurity From 2012 To 2022: Decision-Makers’ Thoughts On Satellite Cybersecurity Evolving, Rachel C. Jones
Survey Of Space Professionals’ Perception Of Satellite Cybersecurity From 2012 To 2022: Decision-Makers’ Thoughts On Satellite Cybersecurity Evolving, Rachel C. Jones
Aerospace Sciences Student Publications
Cyberattacks on space assets are often portrayed in vague terms of doubt and mystery. Several claims depict satellites being compromised or attacked, but little corroboration has been published or made publicly available. As the commercial space industry grows, increased concern with space cybersecurity will prompt commercial satellite decision-makers to analyze the often-undefined risk of cyberattacks against satellites. This article identifies and characterizes the nature of cybersecurity risks to space assets and postulates why space professionals might not prioritize cybersecurity. Additional information was captured from a decadal survey of space professionals conducted in 2012 and 2022. The results show a rise …