4 papers
Attack-Centric by Design: A Program-Structure Taxonomy of Smart Contract Vulnerabilities
Parsa Hedayatnia, Tina Tavakkoli, Hadi Amini +2
Smart contracts concentrate high value assets and complex logic in small, immutable programs, where even minor bugs can cause major losses. Existing taxonomies and tools remain fra…
Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters
Luiz Pereira, M. Hadi Amini
In this paper, we first propose a novel algorithm for model fusion that leverages Wasserstein barycenters in training a global Deep Neural Network (DNN) in a distributed architectu…
Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions
Hadi Amini, Md Jueal Mia, Yasaman Saadati +6
Language models (LMs) are machine learning models designed to predict linguistic patterns by estimating the probability of word sequences based on large-scale datasets, such as tex…
Optimal Quantum Circuit Design via Unitary Neural Networks
M. Zomorodi, H. Amini, M. Abbaszadeh +3
The process of translating a quantum algorithm into a form suitable for implementation on a quantum computing platform is crucial but yet challenging. This entails specifying quant…