LATIDIA · Ciberseguridad

Kerkoporta: Inyección de puertas traseras de salida estructurada en agentes de codificación de razonamiento

arXiv:2611.00138v1 Anuncio Tipo: nuevo Resumen: Los ataques de puerta trasera existentes de modelos de lenguaje grandes (LLM) operan principalmente en entornos de chat, donde el riesgo está limitado por salidas de texto de formato libre. Los agentes de IA eliminan ese límite por

La noticia

arXiv:2611.00138v1 Announce Type: new Abstract: Existing large language model (LLM) backdoor attacks operate primarily in chat settings, where the risk is bounded by free-form text outputs. AI agents remove that bound by performing actions and executing commands on the user's machine. We introduce structured-output backdoor attacks against reasoning models in agentic coding settings. A trigger placed anywhere in the agent's context causes the model to emit an attacker-chosen tool call, which the harness executes, directly compromising the system's confidentiality, integrity, or availability. We present Kerkoporta, a methodology that constructs high-quality poison samples, injects the backdoor via supervised fine-tuning, and recovers utility loss with lightweight reinforcement learning. We evaluate on modern,