Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
The paper proposes a safer way to use LLMs in SOC remediation by putting them behind a SIEM/XDR control plane and a NeMo-Guardrails proxy, so the model can only emit predefined remediation intents whose arguments are validated before endpoint agents execute templated actions. Its main contribution is the defense-in-depth framing—combining alert-grounded intent constraints, command templating, argument validation, and guardrail evaluation on a SOC-specific adversarial corpus—but the work is still more architectural than fully deployed, with OT use only argued by fit and inline autonomous control limited by guardrail latency.
Abstract
Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated alerts and too few analysts. Large Language Models (LLMs) are increasingly proposed as reasoning engines that triage alerts and, in autonomous deployments, issue commands that block IPs, kill processes, or quarantine files on production hosts. This coupling introduces a new risk: a single adversarial alert can become a remote code path through the LLM's reasoning, leading it to recommend an action the SOC then executes. We present a constrained-action architecture with two coordinated layers: (i) a SIEM/XDR control plane that grounds remediation in correlated host events and confines the LLM's output to a closed intent vocabulary whose templated commands are executed by thin endpoint agents, backstopped by an argument validator; and (ii) a NeMo-Guardrails proxy that wraps the SOC-analyst LLM with input- and output-rail policies, evaluated out-of-the-box against a SOC-specific adversarial corpus we release. The stock proxy lifts injection recall from 25.0% to 94.5% at a 0.1% false-positive rate, and a live red-team exercise confirms that the closed intent vocabulary and argument validator contain the observed LLM failure modes before any command crosses the trust boundary. As an architectural fit (not yet a measured operational-technology deployment), the constrained-action property suits critical-infrastructure settings where a wrong remediation has physical, not merely operational, consequences. The loop is best run human-in-the-loop or delayed: the measured rail latency keeps inline control out of scope.