AMD EPYC Secure Encrypted Virtualization Not So Secure: Researchers

[XiGMAKiD]

There's one more thing that looks suspicious.
Their paper is pretty much a slightly modified copycat of this one, published by members of Tangram Technologies from Shanghai back in December.

https://arxiv.org/ftp/arxiv/papers/1712/1712.05090.pdf

Their team lead, ZhaoHui Du, is very notable for being an Intel researcher and software engineer for almost 18 years. It's not a red flag by any means, but considering that Tangram was founded in 2017, it raises some concerns and suspicions.

Intel just wanted to make sure Epyc are safe for customer so they can use it to replace Xeon

 

[BorgOvermind]

While it's great that we're finally getting real security people looking at CPUs, it's terrifying that the manufacturers themselves never did this due diligence.

They look but they don't tell.

That's how intel and seagate got away with complete spy programs until Kas revealed them.

 

[medi01]

"Admins can do evil things"
Totally not FUD campaign against AMD, who is thrashing Intel on multicore front.

 

[Fx]

They are REPLACING the host hypervisor with a new one which is specifically allowed to snoop in the memory accesses. And they still need a VM on the same host to be a web server of allow other kind of memory access to the same ram as the target VM. This cannot be done in a datacenter without collusion with IT administrators from the whole chain of command.
Blaming the manufacturer because the product does not behave the same after the user flashes a new bios is unfathomable.
Even CTS Labs would not stoop so low as to report this a vulnerability.

Exactly. I called BS before I even read it. Sure enough, yet another "vulnerability" when someone has direct access to the servers.

 

[remixedcat]

This "newly discovered vulnerability" is nothing new. People have been circumventing penetrating to the host.

With Parallels virtuozzo containers you can go up the chain of command to infiltrate the host.

More examples here https://en.wikipedia.org/wiki/Virtual_machine_escape

 

[lexluthermiester]

Someone correct me if wrong, this is related to the recent CTS thing? Seems along the same lines..

 

[Patriot]

Someone correct me if wrong, this is related to the recent CTS thing? Seems along the same lines..

It is... But also valid in the same sense as the cts vulnerabilities are. The feature being bypassesed was designed to stop malicious hypervisors, Intel's security researcher managed to find a way around it. And this was published with a degree of separation same as cts.