LATIDIA · Ciberseguridad
Las salvaguardas contra el uso indebido de los LLM se basan en entradas no fiables: una vulnerabilidad generalizada de alto riesgo
arXiv:2607.27951v2 Tipo de anuncio: sustitución Resumen: Los grandes modelos de lenguaje ayudan ahora a profesionales de campos como la ciberseguridad y la biología, pero las mismas respuestas podrían ayudar a un atacante. Los implementadores confían en las medidas de protección contra el uso indebido.
WhatsApp ↗Telegram ↗
La noticia
arXiv:2607.27951v2 Announce Type: replace Abstract: Large language models now help professionals in fields such as cybersecurity and biology, yet the same answers would help an attacker. Deployers rely on misuse safeguards to keep such answers from attackers. We find that these safeguards share a high-risk vulnerability: they decide whether to release an answer from what users write, including the professional identity or purpose they claim, and anyone can write such a claim. Threat reports from model vendors and security firms show that attackers who fabricate a professional identity or purpose already exploit this vulnerability to cause serious harm. The vulnerability is also widespread across the state of the art: every