<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Security on StackSimplify | DevOps &amp; Cloud Education by Kalyan Reddy</title><link>https://stacksimplify.com/tags/security/</link><description>Recent content in Security on StackSimplify | DevOps &amp; Cloud Education by Kalyan Reddy</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 19 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://stacksimplify.com/tags/security/index.xml" rel="self" type="application/rss+xml"/><item><title>ML Security on Kubernetes: 4 Layers Protecting Your Models</title><link>https://stacksimplify.com/blog/ml-security-kubernetes/</link><pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate><guid>https://stacksimplify.com/blog/ml-security-kubernetes/</guid><description>Your model endpoint has no auth. Anyone with the URL gets predictions.
That is not a hypothetical. It is the default on most KServe deployments. Deploy a model, get an endpoint, and it is wide open. No token. No identity check. No network restriction.
ML systems have a unique attack surface: training data, model artifacts, feature stores, and inference endpoints. Each one is a target.
The ML Attack Surface Asset Default Risk Model endpoints Open, returning predictions to anyone Training data S3 buckets with broad IAM access Model artifacts Serialized files that can be swapped or poisoned Feature stores Real-time pipelines with PII and business logic Traditional DevOps secures code.</description></item></channel></rss>