Come join my updated Black Hat class in Las Vegas, "Agentic AI-Aided Kubernetes Attack and Defense!"
Kubernetes and AI are more tightly-coupled than you think - about two thirds of organizations hosting generative AI models use Kubernetes to manage inference workloads (CNCF). And Kubernetes is growing in popularity for hosting streamable MCP servers and remote agents.
We're going to have a blast with new cutting-edge exercises that integrate AI agents into attacking and defending Linux, containers, and Kubernetes. We'll also be attacking a multi-user agentic AI system running on Kubernetes, using both direct and indirect prompt injections, gaining access to the cluster, and adding indirect prompt injection backdoors to the vector database. As in all the other exercises, we'll turn around and harden the system against this.
You can learn more and register here:
https://t.co/v09oU7gDUd
Here's an excerpt of the class description:
Learn how to use agentic AI to aid you as you attack and defend Kubernetes, Linux, and containers, from Jay Beale, who has led development of the Kubernetes CTF at DEF CON and the open source Kubernetes attack tool: Peirates. In this fully hands-on course, you'll get an x86 computer to keep, complete with an agentic AI framework, Kubernetes clusters, and capture the flag virtual machines, which you will attack and defend. You'll also get access to our cloud environment, allowing you to attack cloud-based Kubernetes clusters.
This well-reviewed training focuses on giving you practical attack skills from real penetration tests, coupled with solid defenses to break attacks. You'll create an agentic AI platform with skills and tools that allow your agents to enumerate a cluster, analyze configuration weaknesses, and recommend attack paths.
Every topic in the class has an attack exercise, where you will first compromise a Kubernetes cluster or application. Most have a matching defense exercise, where you will use new skills to break that attack, confident that it will break others.
@Midnight_Captl I have to assume this ask is coming from their customers directly. Model routing based on cost is only going to become more common from here on out.
@VeryChrislike@robertgraham Most of the cost of delivering electricity is fixed cost. Expanding capacity is good actually. Also has the benefit of stabilizing prices in the long term.
@Midnight_Captl@DharmilMehta777 I've not seen anything conclusive to support it, but its just a weird hill to die on with LPX right around the corner either way. Especially so, if your point is that TCO will be lower, which NVDA is going to have a large advantage on for the foreseeable future.
@DharmilMehta777@Midnight_Captl Maybe, but even then, barely, and only for smaller models, but ultimately how does that hold up with LPX coming out q3?
@panopticon0745@business@opinion Aware. They subsidize your property tax. The county couldn't be more clear that it's worth it, like there isn't a better example in the entire country.
@panopticon0745@business@opinion Datacenters aren't even vaguely new to DC. Loudon County somewhat famously collects 50% of their property tax revenue via datacenter taxes: https://t.co/ZU3tToHv3L so you're at best decades too late.
@Mattxduchak@0neBrown@unusual_whales Historical averages of 14% are not good, lol. There were not net employment losses in March or April going back to the pandemic. I thought your point was that things were getting *better*, apparently not. Lemme know when Canada reaches full employment.