Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study investigates the security implications of Agentic Remote Access Trojans (RATs) that leverage Small Language Models (SLMs) for autonomous cyber operations. By implementing an agentic RAT using a locally deployed 8-billion-parameter Dolphin-family model, the researchers demonstrated that the SLM could autonomously interpret reconnaissance data, select actions, and achieve root access on vulnerable systems without human intervention. Although the model showed significant limitations in reliability, completing only 10.9% of a strict checklist, the findings suggest that as SLMs improve, such autonomous threats could become more practical and challenging to detect.
Small Language Models can autonomously execute cyber attacks, achieving root access on vulnerable systems without human oversight, raising urgent security concerns.
Agentic artificial intelligence raises a new security concern: cyber threats that reason, act, and adapt locally without continuous human direction. We examine this threat through an Agentic Remote Access Trojan (agentic RAT): a Remote Access Trojan augmented with a locally deployed Small Language Model (SLM). The SLM interprets host and network observations, selects actions, recovers from failed steps, and reduces reliance on an external operator. We implement the concept in a controlled, network-isolated lab built from Kali Linux, a Metasploitable2 target, LM Studio, and a local 8-billion-parameter Dolphin-family model. We then test whether a model this small can support autonomous cyber decision-making. This is architecturally feasible today. On commodity hardware, with no cloud service and no operator in the loop, the SLM closed the full observe-decide-act cycle: it interpreted ranked reconnaissance evidence supplied by the controller, selected actions, and obtained verified root-shell access on real vulnerable services. However, it is not yet operationally reliable. The same model hallucinated commands, misread output, and recovered from failure inconsistently, completing 10.9% of a deliberately strict checklist. That gap reflects the limits of today's small models, not a ceiling on the concept. As SLMs improve, agentic endpoint systems may become more practical, more autonomous, and harder to detect, straining existing monitoring, containment, and policy-enforcement mechanisms. Real-world incidents in 2025-2026 already show AI-driven intrusions moving from concept toward practice. That makes the local, self-contained variant we study a plausible near-term direction, not a hypothetical one.