Latifur Khan
YOU?
Author Swipe
View article: Integrating Retrieval-Augmented Generation and Thematic NLP for Vaccine Confidence Modeling in Alaska
Integrating Retrieval-Augmented Generation and Thematic NLP for Vaccine Confidence Modeling in Alaska Open
Vaccine misinformation poses a significant public health threat, particularly in communities with varying levels of vaccine confidence. This study investigated vaccine hesitancy across Alaska’s diverse communities by triangulating public s…
View article: Transportation Cyber Incident Awareness through Generative AI-Based Incident Analysis and Retrieval-Augmented Question-Answering Systems
Transportation Cyber Incident Awareness through Generative AI-Based Incident Analysis and Retrieval-Augmented Question-Answering Systems Open
Technological advancements have revolutionized numerous industries, including transportation. While digitalization, automation, and connectivity have enhanced safety and efficiency, they have also introduced new vulnerabilities. With 95% o…
View article: A Large Language Model-Supported Threat Modeling Framework for Transportation Cyber-Physical Systems
A Large Language Model-Supported Threat Modeling Framework for Transportation Cyber-Physical Systems Open
Existing threat modeling frameworks related to transportation cyber-physical systems (CPS) are often narrow in scope, labor-intensive, and require substantial cybersecurity expertise. To this end, we introduce the Transportation Cybersecur…
View article: Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps
Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps Open
As connected and automated transportation systems evolve, there is a growing need for federal and state authorities to revise existing laws and develop new statutes to address emerging cybersecurity and data privacy challenges. This study …
View article: Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities
Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities Open
Knowledge graphs have emerged to be promising datastore candidates for context augmentation during Retrieval Augmented Generation (RAG). As a result, techniques in graph representation learning have been simultaneously explored alongside p…
View article: Challenges in Accessing Surgical Equipment in Pakistan: A Surgical Equipment Journey Perspective
Challenges in Accessing Surgical Equipment in Pakistan: A Surgical Equipment Journey Perspective Open
Background and Objective: In Pakistan, the demand for surgery is not being met due to a shortage of both surgical equipment and healthcare workers. This gap in the availability of surgical equipment hinders the provision of safe surgeries.…
View article: LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
LSEBMCL: A Latent Space Energy-Based Model for Continual Learning Open
Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards p…
View article: A Large Language Model-Supported Threat Modeling Framework for Transportation Cyber-Physical Systems
A Large Language Model-Supported Threat Modeling Framework for Transportation Cyber-Physical Systems Open
Increased reliance on automation and connectivity exposes transportation cyber-physical systems (CPS) to many cyber vulnerabilities. Existing threat modeling frameworks are often narrow in scope, labor-intensive, and require substantial cy…
View article: ConfliBERT: A Language Model for Political Conflict
ConfliBERT: A Language Model for Political Conflict Open
Conflict scholars have used rule-based approaches to extract information about political violence from news reports and texts. Recent Natural Language Processing developments move beyond rigid rule-based approaches. We review our recent Co…
View article: An Automated Vulnerability Detection Framework for Smart Contracts
An Automated Vulnerability Detection Framework for Smart Contracts Open
With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day throug…
View article: Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness Open
The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner’s objective is to progressively acquire new tasks as they arrive over time, while a…
View article: Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness Open
The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner's objective is to progressively acquire new tasks as they arrive over time, while a…
View article: FedFusion: Adaptive Model Fusion for Addressing Feature Discrepancies in Federated Credit Card Fraud Detection
FedFusion: Adaptive Model Fusion for Addressing Feature Discrepancies in Federated Credit Card Fraud Detection Open
The digitization of financial transactions has led to a rise in credit card fraud, necessitating robust measures to secure digital financial systems from fraudsters. Nevertheless, traditional centralized approaches for detecting such fraud…
View article: Consumer Deceleration and Well-being under the conditions of Control over Consumption, Social Class, and Spirituality: A Social Acceleration Perspective
Consumer Deceleration and Well-being under the conditions of Control over Consumption, Social Class, and Spirituality: A Social Acceleration Perspective Open
This paper explains how and when consumer deceleration - the perception of slowed-down temporal experience adds to consumer well-being. This investigation is the first attempt to quantify consumer deceleration (a recently coined concept). …
View article: Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously
Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously Open
The endeavor to preserve the generalization of a fair and invariant classifier across domains, especially in the presence of distribution shifts, becomes a significant and intricate challenge in machine learning. In response to this challe…
View article: Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification Open
Is it possible accurately classify political relations within evolving event ontologies without extensive annotations? This study investigates zero-shot learning methods that use expert knowledge from existing annotation codebook, and eval…
View article: Towards Fair Disentangled Online Learning for Changing Environments
Towards Fair Disentangled Online Learning for Changing Environments Open
In the problem of online learning for changing environments, data are sequentially received one after another over time, and their distribution assumptions may vary frequently. Although existing methods demonstrate the effectiveness of the…
View article: Confidential Execution of Deep Learning Inference at the Untrusted Edge with ARM TrustZone
Confidential Execution of Deep Learning Inference at the Untrusted Edge with ARM TrustZone Open
This paper proposes a new confidential deep learning (DL) inference system with ARM TrustZone to provide confidentiality and integrity of DL models and data in an untrusted edge device with limited memory. Although ARM TrustZone supplies a…
View article: An Automated Vulnerability Detection Framework for Smart Contracts
An Automated Vulnerability Detection Framework for Smart Contracts Open
With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day throug…
View article: Dual Contrastive Learning Framework for Incremental Text Classification
Dual Contrastive Learning Framework for Incremental Text Classification Open
Incremental learning plays a pivotal role in the context of online knowledge discovery, as it encourages large models (LM) to learn and refresh knowledge continuously. Many approaches have been proposed to simultaneously preserve knowledge…
View article: ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence
ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence Open
This study investigates the use of Natural Language Processing (NLP) methods to analyze politics, conflicts and violence in the Middle East using domain-specific pre-trained language models.We introduce Arabic text and present ConfliBERT-A…