Wei Yang Bryan Lim
YOU?
Author Swipe
View article: DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents Open
The reliance of mobile GUI agents on Multimodal Large Language Models (MLLMs) introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information (PII) are often sent to untrusted, third-party routers. The…
View article: CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs
CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs Open
Video Multimodal Large Language Models (V-MLLMs) have shown impressive capabilities in temporal reasoning and cross-modal understanding, yet their vulnerability to adversarial attacks remains underexplored due to unique challenges: complex…
View article: Click with Care: Understanding Cybersecurity Awareness in Digital Financial Transactions in Malaysia
Click with Care: Understanding Cybersecurity Awareness in Digital Financial Transactions in Malaysia Open
In today’s digital age, cybersecurity awareness in financial transactions is critical, especially within the banking sector. Maybank, as Malaysia’s top-ranked bank and one of the leading global financial institutions, must prioritize cyber…
View article: Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning Open
Federated Unlearning (FU) has emerged as a critical compliance mechanism for data privacy regulations, requiring unlearned clients to provide verifiable Proof of Federated Unlearning (PoFU) to auditors upon data removal requests. However, …
View article: Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning Open
Federated Domain Adaptation (FDA) is a Federated Learning (FL) scenario where models are trained across multiple clients with unique data domains but a shared category space, without transmitting private data. The primary challenge in FDA …
View article: Hierarchical Symbolic Pop Music Generation with Graph Neural Networks
Hierarchical Symbolic Pop Music Generation with Graph Neural Networks Open
Music is inherently made up of complex structures, and representing them as graphs helps to capture multiple levels of relationships. While music generation has been explored using various deep generation techniques, research on graph-rela…
View article: Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defense
Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defense Open
Federated Learning (FL) is a promising privacy-preserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the trust…
View article: Green Technologies for the Sustainable Metaverse and Web 3.0
Green Technologies for the Sustainable Metaverse and Web 3.0 Open
The concepts of Metaverse and Web 3.0 have surged in popularity, heralded as the “successor to the mobile Internet.” Web 3.0 represents a transformative shift in the Internet landscape, emphasizing user-centric decentralization. These core…
View article: Table of Contents
Table of Contents Open
View article: Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach
Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach Open
Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption. Schedul…
View article: Towards Green Metaverse Networking Technologies, Advancements and Future Directions
Towards Green Metaverse Networking Technologies, Advancements and Future Directions Open
As the Metaverse is iteratively being defined, its potential to unleash the next wave of digital disruption and create real-life value becomes increasingly clear. With distinctive features of immersive experience, simultaneous interactivit…
View article: Cooperative Resource Management in Quantum Key Distribution (QKD) Networks for Semantic Communication
Cooperative Resource Management in Quantum Key Distribution (QKD) Networks for Semantic Communication Open
Increasing privacy and security concerns in intelligence-native 6G networks require quantum key distribution-secured semantic information communication (QKD-SIC). In QKD-SIC systems, edge devices connected via quantum channels can efficien…
View article: Stochastic Resource Allocation for Semantic Communication-aided Virtual Transportation Networks in the Metaverse
Stochastic Resource Allocation for Semantic Communication-aided Virtual Transportation Networks in the Metaverse Open
The physical-virtual world synchronization to develop the Metaverse will require a massive transmission and exchange of data. In this paper, we introduce semantic communication for the development of virtual transportation networks in the …
View article: Economics of Semantic Communication System: An Auction Approach
Economics of Semantic Communication System: An Auction Approach Open
Semantic communication technologies enable wireless edge devices to communicate effectively by transmitting semantic meaning of data. Edge components, such as vehicles in next-generation intelligent transport systems, use well-trained sema…
View article: Achieving an optimal group structure in a neural architecture search
Achieving an optimal group structure in a neural architecture search Open
The method proposed in this letter searches for an effective group structure of group convolutions in a convolutional neural network that can improve the classification accuracy. The model's group structure is obtained using an effective d…
View article: Dynamic Incentive Mechanism Design for COVID-19 Social Distancing
Dynamic Incentive Mechanism Design for COVID-19 Social Distancing Open
As countries enter the endemic phase of COVID-19, people's risk of exposure to the virus is greater than ever. There is a need to make more informed decisions in our daily lives on avoiding crowded places. Crowd monitoring systems typicall…
View article: CrowdFL: A Marketplace for Crowdsourced Federated Learning
CrowdFL: A Marketplace for Crowdsourced Federated Learning Open
Amid data privacy concerns, Federated Learning (FL) has emerged as a promising machine learning paradigm that enables privacy-preserving collaborative model training. However, there exists a need for a platform that matches data owners (su…
View article: Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges
Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges Open
With the increasing demand for intelligent services, the sixth-generation (6G) wireless networks will shift from a traditional architecture that focuses solely on high transmission rate to a new architecture that is based on the intelligen…
View article: A Full Dive into Realizing the Edge-enabled Metaverse: Visions, Enabling Technologies,and Challenges
A Full Dive into Realizing the Edge-enabled Metaverse: Visions, Enabling Technologies,and Challenges Open
Dubbed "the successor to the mobile Internet", the concept of the Metaverse has grown in popularity. While there exist lite versions of the Metaverse today, they are still far from realizing the full vision of an immersive, embodied, and i…
View article: Semantic Communication Meets Edge Intelligence
Semantic Communication Meets Edge Intelligence Open
The development of emerging applications, such as autonomous transportation systems, are expected to result in an explosive growth in mobile data traffic. As the available spectrum resource becomes more and more scarce, there is a growing …
View article: Stochastic Coded Offloading Scheme for Unmanned Aerial Vehicle-Assisted Edge Computing
Stochastic Coded Offloading Scheme for Unmanned Aerial Vehicle-Assisted Edge Computing Open
Unmanned aerial vehicles (UAVs) have gained wide research interests due to their technological advancement and high mobility. The UAVs are equipped with increasingly advanced capabilities to run computationally intensive applications enabl…
View article: Realizing the Metaverse with Edge Intelligence: A Match Made in Heaven
Realizing the Metaverse with Edge Intelligence: A Match Made in Heaven Open
Dubbed "the successor to the mobile Internet", the concept of the Metaverse has recently exploded in popularity. While there exists lite versions of the Metaverse today, we are still far from realizing the vision of a seamless, shardless, …
View article: A Comparative Study for the Impact of IFRS Convergence on Accounting Quality between Malaysian PLC and Chinese PLC
A Comparative Study for the Impact of IFRS Convergence on Accounting Quality between Malaysian PLC and Chinese PLC Open
The purpose of this research is to examines whether Malaysian PLC (fully converge to IFRS) could achieve better accounting quality as compare with Chinese PLC (non-fully converge to IFRS) or otherwise. And then further study on the relatio…
View article: Optimal Stochastic Coded Computation Offloading in Unmanned Aerial Vehicles Network
Optimal Stochastic Coded Computation Offloading in Unmanned Aerial Vehicles Network Open
Today, modern unmanned aerial vehicles (UAVs) are equipped with increasingly advanced capabilities that can run applications enabled by machine learning techniques, which require computationally intensive operations such as matrix multipli…
View article: Optimal Stochastic Coded Computation Offloading in Unmanned Aerial\n Vehicles Network
Optimal Stochastic Coded Computation Offloading in Unmanned Aerial\n Vehicles Network Open
Today, modern unmanned aerial vehicles (UAVs) are equipped with increasingly\nadvanced capabilities that can run applications enabled by machine learning\ntechniques, which require computationally intensive operations such as matrix\nmulti…
View article: Unified Resource Allocation Framework for the Edge Intelligence-Enabled Metaverse
Unified Resource Allocation Framework for the Edge Intelligence-Enabled Metaverse Open
Dubbed as the next-generation Internet, the metaverse is a virtual world that allows users to interact with each other or objects in real-time using their avatars. The metaverse is envisioned to support novel ecosystems of service provisio…
View article: Economics of Semantic Communication System in Wireless Powered Internet of Things
Economics of Semantic Communication System in Wireless Powered Internet of Things Open
The semantic communication system enables wireless devices to communicate effectively with the semantic meaning of the data. Wireless powered Internet of Things (IoT) that adopts the semantic communication system relies on harvested energy…
View article: Communication-efficient and Scalable Decentralized Federated Edge Learning
Communication-efficient and Scalable Decentralized Federated Edge Learning Open
Federated Edge Learning (FEL) is a distributed Machine Learning (ML) framework for collaborative training on edge devices. FEL improves data privacy over traditional centralized ML model training by keeping data on the devices and only sen…
View article: Decentralized Edge Intelligence: A Dynamic Resource Allocation Framework for Hierarchical Federated Learning
Decentralized Edge Intelligence: A Dynamic Resource Allocation Framework for Hierarchical Federated Learning Open
To enable the large scale and efficient deployment of Artificial Intelligence (AI), the confluence of AI and Edge Computing has given rise to Edge Intelligence, which leverages on the computation and communication capabilities of end devic…
View article: Collaborative Coded Computation Offloading: An All-pay Auction Approach
Collaborative Coded Computation Offloading: An All-pay Auction Approach Open
As the amount of data collected for crowdsensing applications increases rapidly due to improved sensing capabilities and the increasing number of Internet of Things (IoT) devices, the cloud server is no longer able to handle the large-scal…