---
title: "Discussion on \"Defending the AI Perimeter: Mitigating OWASP LLM10 (Model Theft & Data Exfiltration) with GKE Dataplane V2 and eBPF\" | Hashnode"
description: "Discussion on \"Defending the AI Perimeter: Mitigating OWASP LLM10 (Model Theft & Data Exfiltration) with GKE Dataplane V2 and eBPF\". Prevent OWASP LLM10 data exfiltration and model theft in RAG agents using GKE Dataplane V2 eBPF kernel network policies."
url: "https://hashnode.com/posts/mitigating-owasp-llm10-gke-dataplane-v2-ebpf/6a826fe060330f897d41a11c"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Defending the AI Perimeter: Mitigating OWASP LLM10 (Model Theft & Data Exfiltration) with GKE Dataplane V2 and eBPF](https://cloudironguard.hashnode.dev/mitigating-owasp-llm10-gke-dataplane-v2-ebpf?utm_source=hashnode&utm_medium=feed)

Prevent OWASP LLM10 data exfiltration and model theft in RAG agents using GKE Dataplane V2 eBPF kernel network policies.

Aug 17 · 8 min read · cloudironguard.hashnode.dev  
Read the article

-   [#ai-security](https://hashnode.com/tag/ai-security)
-   [#gke-llm-security](https://hashnode.com/tag/gke-llm-security)
-   [#gke](https://hashnode.com/tag/gke)
-   [#llm](https://hashnode.com/tag/llm)
-   [#owasp-top-10](https://hashnode.com/tag/owasp-top-10)
-   [#cloud-security](https://hashnode.com/tag/cloud-security)
-   [#gcp](https://hashnode.com/tag/gcp)
-   [#ai-agents](https://hashnode.com/tag/ai-agents)
-   [#llm-security](https://hashnode.com/tag/llm-security)
-   [#ebpf](https://hashnode.com/tag/ebpf)

## Written by

[Kamran Shaghaghi](https://hashnode.com/@kam-secops)

@kam-secops · Montreal, Canada

  
[View profile](https://hashnode.com/@kam-secops)

Securing the cloud, one packet at a time. Currently building the future of safe MLOps.

I’m a Cloud Infrastructure & Security Engineer who loves solving complex architectural puzzles. Certified in GCP DevOps, Security, and Networking, I spend my time ensuring systems are resilient, automated, and locked down. Right now, my technical playground is at the frontier of MLOps and AI Security—building secure, scalable pipelines for machine learning workloads. On this blog, I write about real-world cloud troubleshooting, infrastructure as code, and the hard-earned lessons of securing modern AI systems. Let’s build things that scale and don’t break.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.