Aggressive-YoYo: Exploiting Intent-Semantic Misalignment in AI-Native 6G Management Planes

Abstract

Intent-Based Networking (IBN) enables operators to express high-level service objectives that are automatically translated into low-level control and orchestration policies. In AI-native 6G management planes, semantic misalignment during this translation can induce unsafe configurations that amplify conventional resource-exhaustion attacks. We investigate this vulnerability through aggressive-YoYo, a compound threat combining YoYo-style burst traffic with prematurely configured Kubernetes readiness probes. We implement an end-to-end intent-to-configuration pipeline that resolves natural-language service intents into structured policies, compiles them into Kubernetes probe settings, and evaluates the resulting behavior using a representative slice-assurance management function on Google Kubernetes Engine (GKE). Controlled readiness-delay experiments show that premature readiness can increase replica provisioning, aggregate CPU and memory consumption, storage activity, and request failures, while inducing non-trivial service-level tradeoffs. Similar resource amplification under a different N1-family machine type and deployment zone indicates that the effect is not specific to a single configuration. We further analyze readiness misconfiguration across multiple Kubernetes scaling mechanisms and derive service-specific safe and amplifying configuration regions. Aggressive-YoYo is also detectable using fully supervised temporal classifiers evaluated with cycle-disjoint testing and feature-set ablation; the best configuration achieves an average accuracy of 92.6% using only real attack traces. Under scarce aggressive-YoYo supervision, limited exposure to aggressive-YoYo traces improves detection over the one-class setting. These results show that intent-semantic misalignment creates measurable cross-layer management risks and motivate semantic validation and telemetry-aware monitoring for trustworthy AI-native 6G orchestration.