6 papers
SPID-Chain: Verifiable Polar-Coded State Validation for Cross-Chain DAG Settlement
Amirhossein Taherpour, Xiaodong Wang
Cross-chain settlement must preserve safety across heterogeneous ledgers while tolerating delayed computation, Byzantine participants, and adversarial transaction issuance. This pa…
Secure Decentralized Federated Learning via Gossip and Virtual Voting
Amirhossein Taherpour, Xiaodong Wang
Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack…
No Certificate, No Execution: Certified Traces as a Foundation for Trustworthy AI Agents
Xiao-Yang Liu Yanglet, Xiaodong Wang, Agostino Capponi
We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger…
ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning
Amirhossein Taherpour, Xiaodong Wang
Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, securi…
PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization
Yang Jiao, Xiaodong Wang, Kai Yang
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications, e.g., medical question-answering, mathematical sciences, and code generat…
A High-throughput and Secure Coded Blockchain for IoT
Amirhossein Taherpour, Xiaodong Wang
We propose a new coded blockchain scheme suitable for the Internet-of-Things (IoT) network. In contrast to existing works for coded blockchains, especially blockchain-of-things, th…