Combatir la destilación adversarial
Las defensas actualizadas en los modelos GPT‑6.2 redujeron drásticamente el éxito de los ataques a la extracción de razonamiento protegido.
OpenAI announced new measures to combat adversarial distillation, a technique where bad actors copy frontier model capabilities without safeguards.
The company added adversarial testing, model training, classifiers and API‑level protections, focusing on preventing extraction of protected reasoning traces.
In internal red‑team tests, the success rate of attacks that recover reasoning dropped from 54.0% on GPT‑6 Astra to 0.2% on GPT‑6.2 Astra after the updates.
OpenAI notes that protecting chain‑of‑thought traces limits the transfer of cyber capabilities to student models, even when tasks are allowed under usage policies.
Defenses operate at request level, limiting trace extraction, and at campaign level, detecting coordinated extraction attempts.
Qué significa para ti
For AI users, stronger safeguards mean reduced risk of models being repurposed for harmful cyber or biological tasks. For developers of free or local models, the focus on protecting reasoning traces highlights a safety approach that may be harder to implement without large‑scale infrastructure.
Fuentes
- Combatting adversarial distillation, OpenAI (official), 20 Nov 2026
Escrito automáticamente a partir de las fuentes anteriores, luego revisado por nuestro código: cada número y nombre debe aparecer en ellas, y ninguna oración puede copiar una fuente. ¿Detectaste un error? Infórmalo.
¿Qué IA puedes usar gratis hoy?
Todos los modelos de IA gratuitos, clasificados por votos humanos ciegos, con la memoria y velocidad que necesita tu GPU.