Security researchers from Invisible Things Lab will be demonstrating (they say) just how easy it is to hack the hypervisor. More specifically, they'll be discussing the (in)security of the Xen hypervisor, such as how to plant rootkits, how to bypass various hypervisor anti-subverting techniques, as well as how "Bluepills" can be used in bare-metal hypervisor compromises. They plan on releasing proof-of-concept code. This could get interesting.On her Invisible Things blog this morning, Joanna Rutkowska (widely known for her research in virtualization security, described three presentations dubbed the "Xen 0wning Trilogy."

Here are the three sessions, in a nutshell:

Subverting the Xen hypervisor. This talk will purportedly show how to modify Xen's hypervisor memory to plant hypervisor rootkits. The claim is that the attack can be done on-the-fly, with no re-boot. Proof-of-concept code will be unleashed. (Oh, joy.)

This talk should gather a crowd, and it'll be interesting to see just how viable (practical) this attack will be in the real world. Hopefully, mitigating controls will be discussed. But they can keep the proof-of-concept code firmly tucked in their pockets, thank you very much.

Detecting and Preventing Xen hypervisor subversions. This talk will focus on the viablility of anti-subversion techniques at protecting the hypervisor. After they show how to bypass these techniques, they'll be demonstrating prototype solutions for hypervisor integrity scanning.

One can only hope the attacks aren't too easily exploited, and multiple (viable) ways to defend the hypervisor will be proposed. Bluepilling the Xen hypervisor. This will be a talk on how to insert malware into the (bare-metal) hypervisor. Invisible Things Lab says the talk will focus on how to slide a Bluepill on top of a running Xen hypervisor. The claim is that this can be done both with, and without, a reboot. They'll also be discussing Bluepill detection methods.

The three tracks will be presented back-to-back, on Aug. 7, at this year's Black Hat conference in Las Vegas. As for why Invisible Things Lab is focusing on Xen? Rutkowska summed it up this way:

It's worth noting that we chose Xen as the target not because we think it's insecure and worthless. On the contrary, we believe Xen is the most secure bare-metal hypervisor out there (especially with all the goodies in the upcoming Xen 3.3). Still, we believe that it needs some improvements when it comes to security. We hope that our presentations will help [in] making Xen (and similar hypervisors) more secure