6 papers · 1 filter
Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling
Chaoyu Zhang, Hexuan Yu, Heng Jin +6
Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these systems often originate from a s…
SpexPay: A Privacy-Preserving Pay-As-You-Go System for Dynamic Spectrum Sharing
Mohaimin Al Barat, Hexuan Yu, Shaoyu Li +5
Dynamic Spectrum Sharing (DSS) is a cornerstone of next-generation wireless systems, yet existing solutions such as Spectrum Access Systems (SAS) rely on centralized administrators…
Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
Heng Jin, Chaoyu Zhang, Hexuan Yu +4
Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delega…
IU-GUARD: Privacy-Preserving Spectrum Coordination for Incumbent Users under Dynamic Spectrum Sharing
Shaoyu Li, Hexuan Yu, Shanghao Shi +4
With the growing demand for wireless spectrum, dynamic spectrum sharing (DSS) frameworks such as the Citizens Broadband Radio Service (CBRS) have emerged as practical solutions to…
FC-GUARD: Enabling Anonymous yet Compliant Fiat-to-Cryptocurrency Exchanges
Shaoyu Li, Hexuan Yu, Md Mohaimin Al Barat +3
With the rise of decentralized finance, fiat-to-cryptocurrency exchange platforms have become popular entry points into the cryptocurrency ecosystem. However, these platforms frequ…
Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
Chaoyu Zhang, Heng Jin, Shanghao Shi +4
Federated Learning (FL) has gained significant attention for its privacy-preserving capabilities, enabling distributed devices to collaboratively train a global model without shari…