activity
20242026
collaborators

20 papers

cs.CR2026

Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation

Zhisheng Qi, Utkarsh Sahu, Li Ma +9

Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory manageme…

cs.DC2026

DynLP: Parallel Dynamic Batch Update for Label Propagation in Semi-Supervised Learning

S M Shovan, Arindam Khanda, S M Ferdous +2

Semi-supervised learning aims to infer class labels using only a small fraction of labeled data. In graph-based semi-supervised learning, this is typically achieved through label p…

cs.LG2026

Knowledge Homophily in Large Language Models

Utkarsh Sahu, Zhisheng Qi, Mahantesh Halappanavar +6

Large Language Models (LLMs) have been increasingly studied as neural knowledge bases for supporting knowledge-intensive applications such as question answering and fact checking.…

cs.LG2025

Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations

Kazi Ashik Islam, Zakaria Mehrab, Mahantesh Halappanavar +5

Coastal flooding poses increasing threats to communities worldwide, necessitating accurate and hyper-local inundation forecasting for effective emergency response. However, real-wo…

cs.DC2025

Anonymized Network Sensing using C++26 std::execution on GPUs

Michael Mandulak, Sayan Ghosh, S M Ferdous +2

Large-scale network sensing plays a vital role in network traffic analysis and characterization. As network packet data grows increasingly large, parallel methods have become mains…

eess.SY2025

On the System Theoretic Offline Learning of Continuous-Time LQR with Exogenous Disturbances

Sayak Mukherjee, Ramij R. Hossain, Mahantesh Halappanavar

We analyze offline designs of linear quadratic regulator (LQR) strategies with uncertain disturbances. First, we consider the scenario where the exogenous variable can be estimated…