Preprint
Aug 2026
Tiny Enough to Break In: Agentic Remote Access Trojans Powered by Small Language Models
This work examines cyber threats that reason, act, and adapt locally without continuous human direction through an Agentic Remote Access Trojan augmented with a locally deployed Small Language Model (SLM), and tests whether a model this small can support autonomous cyber decision-making.
Yu-Han You, S. Adavelly, Victoria Lovelace et al.
· 1 citation