Seminarium: Systemy Rozproszone
5 marca 2026 12:15, sala 4070
Mateusz Wasilewski, Michał Płachta
Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
In recent years, the vision of autonomous AI agents capable of interacting with a wide range of tools and data sources has gained significant momentum.
Model Context Protocol (MCP) is an emerging open standard that defines a unified, bi-directional communication and dynamic discovery protocol between AI models and external tools or resources. It aims to enhance interoperability and reduce fragmentation across diverse systems. Authors also construct a comprehensive threat taxonomy that categorizes security and privacy risks across four major attacker types:
- malicious developers
- external attackers
- malicious users
- security flaws
Zapraszam,
Mateusz Wasilewski
Bibliografia:
HRL-TSCH: A Hierarchical Reinforcement Learning-based TSCH Scheduler for IIoT
This paper introduces HRL-TSCH, a scheduling framework that uses Hierarchical Reinforcement Learning within a Software Defined Networking architecture to manage wireless sensor communication in the Industrial Internet of Things. The model employs a dual policy approach, where a higher level policy manages the activation of communication links, while lower level policies assign specific timeslots and frequency channels. This framework dynamically resolves a multi-objective optimization problem to balance network throughput, delay and power consumption. Zapraszam,
Michał Płachta
Bibliografia: