LATIDIA · Ciberseguridad

Codetta: colusión multiagente de alta capacidad, sin llave e indetectable

arXiv:2609.28900v1 Anuncio Tipo: nuevo Resumen: Los sistemas multiagente construidos sobre grandes modelos de lenguaje (LLM) se implementan cada vez más en entornos de alto riesgo como finanzas, atención médica e ingeniería de software, donde la edad

La noticia

arXiv:2609.28900v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) are increasingly deployed in high-stakes settings such as finance, healthcare, and software engineering, where agents coordinate through natural-language messages. The same channels, however, let colluding agents exfiltrate confidential information or coordinate unauthorized actions, and steganography can hide such communication inside outputs that look ordinary to an auditor reading the transcript. Existing provably undetectable LLM steganography protocols are not suited to realistic deployments. High-capacity schemes assume a symmetric setting where the receiver can reproduce the sender's output distribution, the state-of-the-art protocol for asymmetric agents has very low capacity, and most approaches rely on a pre-shared secret key. We