LATIDIA · Ciberseguridad

Sobre la recuperación privada de conocimientos y la inferencia privada para sistemas multiagente seguros

arXiv:2611.13696v1 Tipo de anuncio: nuevo Resumen: Los sistemas multiagente proporcionan un marco conveniente para el despliegue masivo de agentes basados en modelos de lenguaje grandes (LLM). Proporciona un marco sólido donde los agentes ca

La noticia

arXiv:2611.13696v1 Announce Type: new Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an autonomous way. Agentic AI is the new term to denote these AI-based autonomous systems. In real multi-agent systems, agents need to deal with malicious agents some of which can exploit security vulnerabilities to do harm. A memory poisoning attack is an example of exploiting a vulnerability to modify agents knowledge and, thus, affect its behavior. In an agent, there are different types of memory systems (semantic, episodic, and short-term) which