A Trust-By-Learning Framework For Secure 6g Wireless Networks Under Native Generative Ai Attacks,
2025
University of West Georgia
A Trust-By-Learning Framework For Secure 6g Wireless Networks Under Native Generative Ai Attacks, Md Shirajum Munir, Sravanthi Proddatoori, Manjushree Muralidhara, Trinidad Mario Dena, Walid Saad, Zhu Han, Sachin Shetty
Center for Secure and Intelligent Critical Systems (CSICS) Publications
Sixth-generation (6G) wireless networks will become vulnerable due to native generative AI (GenAI)-driven intelligent poisoning attacks in both the radio unit and the core network. In particular, network parameters and metrics in cross-layer design pose fundamentally uncertain conditions and can be compromised through the native GenAI mechanism, which leverages data augmentation and reconstruction capabilities. This work investigates the capabilities of native GenAI to create novel poisoning attacks in wireless networks, while investigating their impact through uncertainty-informed root analysis. Then, detected attacks are mitigated by developing a trustworthy service aggregation in the wireless network. First, a joint decision problem is formulated …
The Effectiveness Of Tech Support Fraud In Damaging Older Individual’S Financial Security,
2025
Edith Cowan University
The Effectiveness Of Tech Support Fraud In Damaging Older Individual’S Financial Security, Vanessa Perera
Theses : Honours
This study discovers the tactics employed to create detrimental effects upon older people impacted from fraudulent tech-support incidents. It examines social engineering, and financial confusion of older people. This is significant considering adaptations towards digital banking and payment management. This research looked at online and active over 65s. Using largely qualitative approaches over 65s were interviewed and responses validated against cyber-professionals’ responses. This identified three key findings: older adults feel confused and misunderstand tech support scams; threat actors build trust by pretending to offer technical help but use this to deceive their victims; and older adults face serious social and …
Sting: A Stealthy Backdoor Attack On Gnn-Based Malicious Domain Detection Via Dns Perturbations,
2025
Alfaisal University
Sting: A Stealthy Backdoor Attack On Gnn-Based Malicious Domain Detection Via Dns Perturbations, Muhammad Anan, Mahmoud Nazzal, Abdallah Khreishah, Issa Khalil, Nhathai Phan, Ahmad Sawalmeh
Computer Science Faculty Publications
Detecting malicious Internet domains is essential for safeguarding against various online threats. The current approach to detecting malicious domains (MDD) employs a graph neural network (GNN) method, which uses DNS logs to construct heterogeneous graphs for determining the maliciousness of unknown domains. Despite its success, this method is vulnerable to data poisoning attacks where an adversary can manipulate specific graph nodes to implant a backdoor into the model during training. To showcase the vulnerability, we propose a stealthy trigger injection attack on node features and graph structure in MDD, dubbed (STING). The attacker carefully manipulates selected features and edges of …
Understanding Pii Leakage In Large Language Models: A Systematic Survey,
2025
Zhejiang University
Understanding Pii Leakage In Large Language Models: A Systematic Survey, Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, Fang Zhang
Computer Science Faculty Publications
Large Language Models (LLMs) have demonstrated exceptional success across a variety of tasks, particularly in natural language processing, leading to their growing integration into numerous facets of daily life. However, this widespread deployment has raised substantial privacy concerns, especially regarding personally identifiable information (PII), which can be directly associated with specific individuals. The leakage of such information presents significant real-world privacy threats. In this paper, we conduct a systematic investigation into existing research on PII leakage in LLMs, encompassing commonly utilized PII datasets, evaluation metrics, and current studies on both PII leakage attacks and defensive strategies. Finally, we identify unresolved …
Privshap: A Finer-Granularity Network Linearization Method For Private Inference,
2025
Old Dominion University
Privshap: A Finer-Granularity Network Linearization Method For Private Inference, Xiangrui Xu, Zhenzhen Wang, Rui Ning, Chunsheng Xiu, Hongyi Wu
Computer Science Faculty Publications
Private inference applies cryptographic techniques like homomorphic encryption, garble circuit and secret sharing to keep both sides privacy in a client-server setting during inference. It is often hindered by the high communication overheads, especially at non-linear activation layers such as ReLU. Hence ReLU pruning has been widely recognized as an efficient way to accelerate private inference. Existing approaches to ReLU pruning typically rely on coarse hypothesis, which assume an inverse correlation between the importance of ReLU and linear layers or shallow activation layers have less importance for universal models, to assign the budgets according to the layer while preserving the …
Position: Benchmarking Is Broken - Don't Let Ai Be Its Own Judge,
2025
Princeton University
Position: Benchmarking Is Broken - Don't Let Ai Be Its Own Judge, Zerui Cheng, Stella Wohnig, Ruchika Gupta, Samiul Alam, Tassallah Abdullahi, João Alves Ribeiro, Christian Nielsen-Garcia, Saif Mir, Siran Li, Jason Orender, Seyed Ali Bahrainian, Daniel Kirste, Aaron Gokaslan, Carsten Eickhoff, Pramod Viswanath, Ruben Wolff
Computer Science Faculty Publications
The meteoric rise of Artificial Intelligence (AI), with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as current benchmarks increasingly reveal critical vulnerabilities. Issues like data contamination and selective reporting by model developers fuel hype, while inadequate data quality control can lead to biased evaluations that, even if unintentionally, may favor specific approaches. As a flood of participants enters the AI space, this "Wild West" of assessment makes distinguishing genuine progress from exaggerated claims exceptionally difficult. Such ambiguity blurs scientific signals …
Not Here, Go There: Analyzing Redirection Patterns On The Web,
2025
Old Dominion University
Not Here, Go There: Analyzing Redirection Patterns On The Web, Kritika Garg, Sawood Alam, Dietrich Ayala, Michele C. Weigle, Michael L. Nelson
Computer Science Faculty Publications
URI redirections are integral to web management, supporting structural changes, SEO optimization, and security. However, their complexities affect usability, SEO performance, and digital preservation. This study analyzed 11 million unique redirecting URIs, following redirections up to 10 hops per URI, to uncover patterns and implications of redirection practices. Our findings revealed that 50% of the URIs terminated successfully, while 50% resulted in errors, including 0.06% exceeding 10 hops. Canonical redirects, such as HTTP to HTTPS transitions, were prevalent, reflecting adherence to SEO best practices. Non-canonical redirects, often involving domain or path changes, highlighted significant web migrations, rebranding, and security risks. …
Adversarially Attacking Graph Properties And Sparsification In Graph Learning,
2025
Old Dominion University
Adversarially Attacking Graph Properties And Sparsification In Graph Learning, Chunjiang Zhu, Blake Gaines, Jing Deng, Jinbo Bi
Computer Science Faculty Publications
Graph neural networks and graph transformers explicitly or implicitly rely on fundamental properties of the underlying graph, such as spectral properties and shortest-path distances. However, it is still not clear how these graph properties are vulnerable to adversarial attacks and what impacts this has on the downstream graph learning. Moreover, while graph sparsification has been used to improve computational cost of learning over graphs, its susceptibility to adversarial attacks has not been studied. In this paper, we study adversarial attacks on graph properties and graph sparsification and their impacts on downstream graph learning, paving the way for how to protect …
Effective Pii Extraction From Llms Through Augmented Few-Shot Learning,
2025
Zhejiang University
Effective Pii Extraction From Llms Through Augmented Few-Shot Learning, Shuai Cheng, Shu Meng, Haitao Xu, Haoran Zhang, Shuai Hao, Chuan Yue, Wenrui Ma, Meng Han, Fang Zhang, Zhao Li
Computer Science Faculty Publications
Large Language Models (LLMs) exhibit strong natural language processing capabilities but also pose significant privacy risks, particularly regarding the leakage of Personally Identifiable Information (PII) embedded in their training data. Existing PII extraction methods suffer from the limitations of low success rates or impracticality for large-scale PII extraction. In this study, we propose a novel PII extraction approach based on enhanced few-shot learning techniques, which achieves efficient and cost-effective PII retrieval without relying on fine-tuning or jailbreaking. We evaluated our approach on both open-source and closed-source LLMs. The experimental results demonstrate that, for non-targeted PII extraction, the attack success rate …
Enhancing Cyber Situational Awareness Through Dynamic Adaptive Symbology: The Dass Framework,
2025
Old Dominion University
Enhancing Cyber Situational Awareness Through Dynamic Adaptive Symbology: The Dass Framework, Nicholas Macrino, Sergio Pallas Enguita, Chung-Hao Chen
Electrical & Computer Engineering Faculty Publications
The static nature of traditional military symbology, such as MIL-STD-2525D, hinders effective real-time threat detection and response in modern cybersecurity operations. This research introduces the Dynamic Adaptive Symbol System (DASS), a novel framework enhancing cyber situational awareness in military and enterprise environments. The DASS addresses static symbology limitations by employing a modular Python 3.10 architecture that uses machine learning-driven threat detection to dynamically adapt symbol visualization based on threat severity and context. Empirical testing assessed the DASS against a MIL-STD-2525D baseline using active cybersecurity professionals. Results show that the DASS significantly improves threat identification rates by 30% and reduces response …
Machine Learning For Computer-Aided Diagnostics From Complex Medical Images,
2025
Edith Cowan University
Machine Learning For Computer-Aided Diagnostics From Complex Medical Images, Afsah Saleem
Theses: Doctorates and Masters
Machine learning has significantly transformed medical image analysis in the current age of artificial intelligence offering vast potential in improving disease diagnosis and management. Cardiovascular diseases (CVDs) are among the leading cause of global mortality, emphasizing the need for early detection for effective intervention and prevention. Abdominal Aortic Calcification (AAC) is an early indicator and contributor to Atherosclerotic Cardiovascular Diseases (ASCVDs) and is commonly assessed through imaging modalities such as computed tomography (CT), X-rays, and Dual-energy X-ray Absorptiometry (DXA). Among these, lateral spine DXA scans, commonly used for osteoporosis screening, offer a cost-effective and low-radiation opportunity for opportunistic CVD risk …
Blockchain-Based Trust Model For Inter-Domain Routing,
2025
Edith Cowan University
Blockchain-Based Trust Model For Inter-Domain Routing, Qiong Yang, Li Ma, Sami Ullah, Shanshan Tu, Hisham Alasmary, Muhammad Waqas
Research outputs 2022 to 2026
Border Gateway Protocol (BGP), as the standard inter-domain routing protocol, is a distance-vector dynamic routing protocol used for exchanging routing information between distributed Autonomous Systems (AS). BGP nodes, communicating in a distributed dynamic environment, face several security challenges, with trust being one of the most important issues in inter-domain routing. Existing research, which performs trust evaluation when exchanging routing information to suppress malicious routing behavior, cannot meet the scalability requirements of BGP nodes. In this paper, we propose a blockchain-based trust model for inter-domain routing. Our model achieves scalability by allowing the master node of an AS alliance to transmit …
Enhancing Cybersecurity Through Autonomous Knowledge Graph Construction By Integrating Heterogeneous Data Sources,
2025
Edith Cowan University
Enhancing Cybersecurity Through Autonomous Knowledge Graph Construction By Integrating Heterogeneous Data Sources, Hatoon Alharbi, Ali Hur, Hasan Alkahtani, Hafiz Farooq Ahmad
Research outputs 2022 to 2026
Cybersecurity plays a critical role in today’s modern human society, and leveraging knowledge graphs can enhance cybersecurity and privacy in the cyberspace. By harnessing the heterogeneous and vast amount of information on potential attacks, organizations can improve their ability to proactively detect and mitigate any threat or damage to their online valuable resources. Integrating critical cyberattack information into a knowledge graph offers a significant boost to cybersecurity, safeguarding cyberspace from malicious activities. This information can be obtained from structured and unstructured data, with a particular focus on extracting valuable insights from unstructured text through natural language processing (NLP). By storing …
Joint 3d Beamforming-And-Trajectory Design For Uav-Satellite Uplink Covert Communication,
2025
Edith Cowan University
Joint 3d Beamforming-And-Trajectory Design For Uav-Satellite Uplink Covert Communication, Jihong Yu, Yuting Cai, Shihao Yan, Yun Li, Jingjing Wang, Jiahao Liu, Jianping An
Research outputs 2022 to 2026
In this paper,we study uplink covert communication in a space-air system,where an unmanned aerial vehicle (UAV) transmits sensitive data to a Geosynchronous Earth Orbit (GEO) satellite while preventing the transmission action from being discovered by a warden. We derive the optimal decision threshold of the warden. We investigate the 3-dimensional (3D) beamformer and 3D trajectory design for the transmitter UAV against this optimum warden to maximize the covert transmission rate in the presence of imperfect channel state information and uncertain noise. Due to the non-convex structure and dependence between beamforming vectors and locations of the transmitter UAV,we develop a decoupling …
Interactive Visualization Workflows For Mitigating Analytical Uncertainty,
2024
New Jersey Institute of Technology
Interactive Visualization Workflows For Mitigating Analytical Uncertainty, Kaustav Bhattacharjee
Dissertations
This dissertation takes a process-centric and stakeholder-first perspective for handling analytical uncertainty: the form of uncertainty that confronts data analysts' insight-generation processes in high-consequence decision-making scenarios. The cost of an incorrect decision when data is used for movie recommendations as opposed to when personal data is used to drive insights or when data-driven modeling is used to drive real-time decisions for maintaining the health of a grid are vastly different in terms of consequences. This dissertation looks at analytical uncertainty in two real-world scenarios: i) how sensitive information leakage can be prevented during the open data release process with data …
Text-To-Text Generative Approach For Enhanced Complex Word Identification,
2024
Edith Cowan University
Text-To-Text Generative Approach For Enhanced Complex Word Identification, Patrycja Śliwiak, Syed Afaq Ali Shah
Research outputs 2022 to 2026
This paper presents a novel approach for solving the Complex Word Identification (CWI) task using the text-to-text generative model. The CWI task involves identifying complex words in text, which is a challenging Natural Language Processing task. To our knowledge, it is a first attempt to address CWI problem into text-to-text context. In this work, we propose a new methodology that leverages the power of the Transformer model to evaluate complexity of words in binary and probabilistic settings. We also propose a novel CWI dataset, which consists of 62,200 phrases, both complex and simple. We train and fine-tune our proposed model …
Digital Twin And Cybersecurity In Additive Manufacturing,
2024
Mississippi State University
Digital Twin And Cybersecurity In Additive Manufacturing, Lidong Wang
Journal of Cybersecurity Education, Research and Practice
Additive manufacturing (AM) has been applied to automotive, aerospace, medical sectors, etc., but there are still challenges such as parts’ porosity, cracks, surface roughness, intrinsic anisotropy, and residual stress because of the high level of thermal gradient. It is significant to conduct the modeling and simulation of the AM process and achieve quality products. Digital Twin (DT) can help AM with forecasting defects/errors through simulation and real-time process monitoring. DT is a concept of Industry 4.0, and its digital structure reflects the real-time behaviors of a cyber-physical or physical system. This paper introduces the progress of DT applications in AM, …
Enhancing Cybersecurity Strategies Through Automated Cti Extraction, Risk Prioritization, And Privacy-Conscious Information Sharing,
2024
University of Arkansas Little Rock
Enhancing Cybersecurity Strategies Through Automated Cti Extraction, Risk Prioritization, And Privacy-Conscious Information Sharing, Spencer Rian Massengale
Theses and Dissertations
Cybersecurity operations require the ability to collect and analyze large amounts of cyber threat intelligence (CTI) to assess risks and formulate defensive strategies against emerging threats. This task has become increasingly complex due to the rapid evolution of cyber threats and the growing volume of unstructured, natural-language CTI sources. The scale of data and analysis needed to utilize CTI effectively far exceeds humans' manual capacity, especially for organizations with limited resources. This research focuses on leveraging Large Language Models (LLMs) and machine learning techniques to enhance CTI extraction, risk assessment, and data sharing. We utilized LLMs to automate the extraction …
The Impact Of Student Engagement Activities On Future Climate Change Adaptation: The Case Of Student Simulation Models,
2024
Youth Leaders Foundation YLF
The Impact Of Student Engagement Activities On Future Climate Change Adaptation: The Case Of Student Simulation Models, Bassel Mostafa Elkalaf
Future Journal of Social Science
This paper explores the critical role of student engagement in addressing the growing challenges of climate change, with a focus on the Model United Nations (MUN) as a case study. As climate-related security threats increase globally, educational platforms that prepare youth for effective leadership in climate politics are more essential than ever. MUN, a widely practiced student activity simulating global policy-making, provides a valuable opportunity for students to deepen their understanding of the interconnectedness between climate change, peace, and security. By participating in MUN simulations, students engage in debates, develop innovative solutions, and practice diplomatic skills, all while exploring the …
Toward An Insider Threat Education Platform: A Theoretical Literature Review,
2024
Dakota State University
Toward An Insider Threat Education Platform: A Theoretical Literature Review, Haywood Gelman, John D. Hastings, David Kenley, Eleanor Loiacono
Research & Publications
Insider threats (InTs) within organizations are small in number but have a disproportionate ability to damage systems, information, and infrastructure. Existing InT research studies the problem from psychological, technical, and educational perspectives. Proposed theories include research on psychological indicators, machine learning, user behavioral log analysis, and educational methods to teach employees recognition and mitigation techniques. Because InTs are a human problem, training methods that address InT detection from a behavioral perspective are critical. While numerous technological and psychological theories exist on detection, prevention, and mitigation, few training methods prioritize psychological indicators. This literature review studied peer-reviewed, InT research organized by …
