Attack Steals Crypto Key From Co-Located Virtual Machines 73
Gunkerty Jeb writes "Side-channel attacks against cryptography keys have, until now, been limited to physical machines. Researchers have long made accurate determinations about crypto keys by studying anything from variations in power consumption to measuring how long it takes for a computation to complete. A team of researchers from the University of North Carolina, University of Wisconsin, and RSA Security has ramped up the stakes, having proved in controlled conditions (PDF) that it's possible to steal a crypto key from a virtual machine. The implications for sensitive transactions carried out on public cloud infrastructures could be severe should an attacker land his malicious virtual machine on the same physical host as the victim. Research has already been conducted on how to map a cloud infrastructure and identify where a target virtual machine is likely to be."
Not just 'a' crypto key (Score:5, Informative)
The published paper is an interesting read. Obtaining the crypto key to libgcrypt is only one application. In general, the authors say, it is possible to construct a side-channel attack on other, unrelated, processes in the attacked VM.
Re: (Score:1)
since you read it, what does this mean? that you can see into another vm from a different one? or from the hyperviser? (which should be obvious)
Re: (Score:3)
"See" from one VM into another, on the same physical hardware. It's a cache-based attack; the attacker fills the cache lines of the CPU, then yields and hopes the hypervisor schedules the other VM on the same CPU core next, and that the other VM is executing a particular set of cryptographic operations. These operations have a very specific behavior with regard to the processor cache. When the attacker's process runs again, it determines which of its cache lines were flushed, and this information tells it s
Re: (Score:2)
See, all the VM needs to do to avoid this attack, is to alter the set of cryptographic operations executed on the CPU, so that no matter what value is in each bit key position, the same cache lines will get dirtied.
If a Key bit being '1' has a different computation than a key bit being '0', then perform both computations, and discard the result of the unneeded one.
Don't trust hardware you don't own. (Score:5, Insightful)
"public cloud infrastructure". The very thought of that makes me cringe, then laugh at the absurdity of it.
We can't even code bug free operating systems. What makes anyone think we can code a bug free hypervisor? I'm still confused as to why people believe that VMs are inherently secure- are they secure because VMware/Xen/Oracle says they are? Or are they secure because they've been tried and tested in the fires of time? All I ever see about hypervisors these days is some inflated marketing terms or new "cloud" interoperability features or some other random junk that solves an imaginary problem someone first had to go out of their way to create. I've never seen anyone actually come out and say "This version of our hypervisor is even more secure then the last because of XYZ!".
The company I work for makes extensive use of "cloud influenced" features in-house. It's awesome to be able to two-click a LAMP stack into existence through a nice web portal or do the same for a couple of Win2K8 instances. Some idiot was preaching about outsourcing our hardware to someone else and putting everything "in the cloud". Luckily management saw it for the farce it was and put that guy in his place pretty quickly.
So again, I'm really curious as to why people explicitly trust: A) Their services/platforms to someone other then themselves, and B) expect that VM hypervisors are bullet proof.
Re:Don't trust hardware you don't own. (Score:5, Insightful)
Well a hypervisior is in theory a simpler beast than a operating system. Depending on your prespective it has less attack surface. I think thoes are good reasons to think we could get it right. The real source of trouble is the x86 world just does not provide the hardware isolation features needed.
Re: (Score:1)
The real source of trouble is the x86 world just does not provide the hardware isolation features needed.
Not true. Highly secure operating systems have been built on the x86 architecture. For example, see the GEMSOS (Gemini Secure Operating System), evaluated at the highest DoD security level (A1, in the old Trusted Computer Evaluation Criteria) and still a commercial product.
The problem is not the hardware isolation features, it's that OS developers don't take advantage of them. And, even more importantly, they don't follow secure development practices. Hypervisors are smaller than general purpose operating s
Re:Don't trust hardware you don't own. (Score:5, Interesting)
I don't think reasonable people expect hypervisors to be bulletproof. Security is a sliding scale though, and for many purposes the security level offered by a responsible cloud provider is good enough for what they're hosting there. If my bank hosted their critical system in AWS, I'd freak out. If Pandora hosts systems there to stream music to me? I could care less. If Pandora puts their billing system there that has my credit card number? Ok, I start to care a little more, but the risk is manageable if they're being careful about the design, and ultimately if someone rips their whole CC database, my CC company or I will notice the fraud activity quickly and issue me a new card. Life goes on.
Why do companies want to use virtualized infrastructure in the first place? Because it offloads work that's not directly relevant to their business. Let me quote directly from Bruce Perens' recent Ask Slashdot responses:
There is no point in having your own programmers write anything that is not a customer-visible business differentiator for your company if you can get it from the Open Source community. A “business differentiator” in this case means something that makes your company look better than a competitor, to the customer directly. Too much “glue code”, and “infrastructure” is written by organizations that have no real need to do so if they would adopt Open Source. The message that is driving them to do so is the huge stack of cash being made by the companies that do use us.
He was talking about it making sense for companies to build on top of OSS lower-layers. The same applies to the cloud infrastructure stuff. For most businesses, infrastructure is not a differentiator anymore. Why have company employees concerned with managing network switches, racks, cooling systems, datacenter fire protection codes and systems, insurance, servers? Or calling vendors and leading them in the building to replace failed drives and RAM modules, or even giving a crap about hardware at all?
If my company's purpose in life is to deliver, e.g., some social iPhone app and a backend network service that supports it, I have no differentiating interest in that level of infrastructure. I still need an IT department, but it can be a small one focused on using that cloud infrastructure correctly (e.g. security, configuration management, etc). When you can shift off that whole layer of complexity to a large-scale specialist, you've reduced the total complexity your company has to manage directly. Focus on the areas that matter, not the common ground. Did your company design, engineer, and build its own kitchen appliances for the company breakroom? Didn't think so...
Re: (Score:2)
Re: (Score:2)
Re:Don't trust hardware you don't own. (Score:4, Insightful)
When you can shift off that whole layer of complexity to a large-scale specialist, you've reduced the total complexity your company has to manage directly. Focus on the areas that matter, not the common ground. Did your company design, engineer, and build its own kitchen appliances for the company breakroom? Didn't think so...
Surely in handing over responsibility for managing that complexity, you also hand over control of what could be intensely critical components of your business. They may do a perfectly good job at a lower cost, but in the (hopefully infrequent) event that the shit hits the fan, the job of fixing it is out of your hands and out of your control and that ought to be scary.
I don't know. Maybe it makes enough sense in the bulk of cases to be a good plan, but the risk of having your entire infrastructure yanked out from under you because of a black swan event or just a regular-grade fuck-up at an unrelated company sounds like something best avoided.
Re: (Score:2)
Perfectly said but, when you are giving away the keys you are trusting your cloud provider 100%.
When your boss asks you, are we 100% sure that we can trust the cloud what would you say?
The government/hacker group can come to your cloud provider and shut you down base on something done without warning. Usually done by one of your employees, or the cloud provider employees. Probably they were hosting something illegal/controversial in your cloud space without you knowing. How do you recover? How do you setup
Re: (Score:2)
Re: (Score:3, Insightful)
I'm still confused as to why people believe that VMs are inherently secure
You're missing the point. No system is secure. What's nice about VMs is ... as many as you need, same price. So just chuck them often, don't even worry about checking them to see if they've been compromised. How awesome would it be if we could just destroy and replace physical desktops and servers 100 times a day? That would get expensive... but not with VMs, which allows you to move the security layer back to the image, and screw securing the actual running system.
Re: (Score:1)
I'm still confused as to why people believe that VMs are inherently secure
You're missing the point. No system is secure. What's nice about VMs is ... as many as you need, same price. So just chuck them often, don't even worry about checking them to see if they've been compromised. How awesome would it be if we could just destroy and replace physical desktops and servers 100 times a day? That would get expensive... but not with VMs, which allows you to move the security layer back to the image, and screw securing the actual running system.
Nice. So it sets a time limit on attacks... to be successful, they'd have to infiltrate before the VMs scheduled destruction and replacement... and all VMs, compromised or not, have a clocked lifetime. Whatever the attacker is trying to do, they must do it fast, because the destruction of their target forces them to begin again.
Re: (Score:2)
I'm still confused as to why people believe that VMs are inherently secure
You're missing the point. No system is secure. What's nice about VMs is ... as many as you need, same price. So just chuck them often, don't even worry about checking them to see if they've been compromised. How awesome would it be if we could just destroy and replace physical desktops and servers 100 times a day? That would get expensive... but not with VMs, which allows you to move the security layer back to the image, and screw securing the actual running system.
Yes... That way they can re-build the vulnerable system. I hear it takes a long time to steal credit card information...
Re: (Score:2, Informative)
I'm still confused as to why people believe that VMs are inherently secure
You're missing the point. No system is secure. What's nice about VMs is ... as many as you need, same price. So just chuck them often, don't even worry about checking them to see if they've been compromised. How awesome would it be if we could just destroy and replace physical desktops and servers 100 times a day? That would get expensive... but not with VMs, which allows you to move the security layer back to the image, and screw securing the actual running system.
Yes... That way they can re-build the vulnerable system. I hear it takes a long time to steal credit card information...
You're not seeing it. The system isn't vulnerable until the attack gains control of image construction. The time between VM destruction and replacement can be quite small... every minute if you wish, the hardware and software can handle this with no interruption of service. Let's see an attacker infiltrate a VM, and then successfully perform a side attack on another VM, and get what they're after, in under a minute. Likely, however, security checking is what occurs every minute or less (hash comparisons or
Re: (Score:2)
Re:Don't trust hardware you don't own. (Score:5, Informative)
I think the details of what's actually been done are relevant here.
This is a side-channel attack against a specific piece of code which has a very clear operational signature.
It's a brute-force implementation of exponentiation mod p using repeated squaring, such that bits from the key directly result in jump operations, and one side of the jump is very cheap and one side is very expensive. Modern implementations of the same exponentiation process (e.g. in OpenSSL) have optimizations which prevent this from being the case.
It is amazing that it's been done at all, but the number of assumptions it rests on regarding precisely what the other VM is running do seem to make it an attack of little practical value. This is more a piece of interesting math than it is an indictment of cross-VM security. And the appropriate response is probably some more neat math to make an algorithm for the same problem which is provably not attackable via this methodology.
Re: (Score:2)
Actually, cache attacks have existed, and been well-known in the cryptographic community, for a *long* time. The only thing that sets this attack apart from the others in history is the fact that the attack was carried out across two VMs (different logical machines, same physical one), rather than across two processes on the same (logical) machine. That's a significant finding, to be sure, but it's not even a new idea to try it; the novelty is that the researchers succeeded.
Re: (Score:2)
And the appropriate response is probably some more neat math to make an algorithm for the same problem which is provably not attackable via this methodology.
The reason this attack works is because they can force a known memory state and then watch for changes.
Changing your encryption isn't going to fix it. Mucking up the L1 Cache will.
There might be a small performance penalty involved with screwing around with the L1, but that's better than the alternative.
I'm also amused that "A team of researchers from the University of North Carolina, University of Wisconsin, and RSA Security"
think "âoeAt present, this is a fairly elaborate attack and we would expect i
Re:Don't trust hardware you don't own. (Score:4, Interesting)
I'm really curious as to why people explicitly trust: A) Their services/platforms to someone other then themselves
The hosting providers have a financial interest in being trustworthy. If they lose the trust, they lose their business. Doing it yourself has its own failure modes too.
Also, for many new companies running their own datacenter would be cost-prohibitive, so trusting may be the only choice they have.
Re: (Score:2)
The hosting providers have a financial interest in being trustworthy.
Oh, you must be referring to EBS*. There are only two reasons why "Teh Cloudz" are so popular right now. It's sexy to do (like outsourcing was 10 years ago), and PHB doesn't have to staff an Admin to keep a Hypervisor up. In a few years, the cost of Cloud computing along with massive outages when things do go wrong, are going to be prohibitive to it's longevity. It's a fad. Being sold on the assumption of 100% uptime. First time PHB gets a scathing call from the CEO because EBS coughed a hairball, he will
Re: (Score:2)
Oh, you must be referring to EBS*.
I'm aware, thanks. I don't have any stuff running on AWS in the US, but I lost some volumes the last time they had an EBS meltdown at eu-west-1. That was expected, they even give an expected yearly failure rate for those. Good thing I was taking snapshots as recommended.
(I was much more concerned about the fact that the same incident revealed a data loss bug in their snapshot code. Good thing I also back up outside their infrastructure.)
It's a fad. Being sold on the assumption of 100% uptime.
Computing is a fad. Being sold on the assumption of increased efficienc
Re: (Score:2)
Re:Who would have thought...... (Score:4, Insightful)
No, it isn't since modern operating systems tend to isolate programs from each other, and in the case of this article the programs are even running in disparate virtual machines, which should put a wall between the two. It is only through exploiting the processor cache that the key could be extracted. The attacker monitors how the victim fills the instruction cache. Since the victim's crypto algorithm follows different code paths depending on the key, the researchers were able to determine key.
This kind of side-channel attack was not universally thought practical so this is news and would be good to think about how to mitigate this problem.
Re: (Score:2)
would be good to think about how to mitigate this problem.
Simple: Use a different core / cache for different VM instances... Oh, wait.
change the algorithm (Score:3)
If necessary you could simply do unnecessary work on one of the code paths so that they end up doing the same amount of work on each path.
Re: (Score:1)
All timing attacks are done in controlled conditions. This is extremely important. Most of them don't work well, if it all, in busy environments.
And what do you know about who's controlling the conditions when you host your data in "the cloud"?
Re:Hypervisor leaks cached data (Score:4, Insightful)
It appears that the hypervisor leaks data from one VM to another by not clearing a cache.
What is leaked is not actually the data in the cache; another virtual machine running on the same computer cannot access that data. What is leaked is some information about cache usage, which may then allow an attacker to find out what the other VM has been doing. The attacker fills the cache with data, switches to another VM, and when it gets control again, the attacker measures how long it takes to access the data that it put into the cache itself. If it's fast, then the attacker knows that the other VM hasn't touched that part of the cache. If it's slow, the attacker knows that the other VM touched this part of the cache.
Re: (Score:2)
If it's slow, the attacker knows that the other VM touched this part of the cache.
Um... no. It knows that the cache has been touched by another VM. There's no guarantee that it was the target VM.
Re: (Score:1)
I doubt that. Pulling this attack off in an UNcontrolled environment will be damn near next to impossible, no matter how good these people think they are.
Modern clouds shuffle VM execution in realtime from hardware to hardware to hardware on a continuous basis, depending on where resources are available, and where they are in demand, at any given time.
In any case, a user's inability to use a system properly is not cause for AMD or Intel to run off and start changing their architecture. This "problem" is one
Re: (Score:3)
Problem is that a leak of any PII data for customers of a business is a PR nightmare and potentially a largish lawsuit costing millions. Millions may be more than was saved by virtualizing.
Re: (Score:3)
like everything, it depends on circumstances (Score:2)
Suppose I have 4 build machines, each running a different OS or version of the OS. At any given time I only need to be building 1 version.
If I virtualize them, I can use one machine (with 4x the disk space). Even accounting for reliability (and getting better redundancy than before) I can get away with 2 machines instead of 4.
Re: (Score:2)
It depends on the task at hand:
I have multiple virtual machines for various tasks, and it isn't just for security. It is also for separation of duties:
One VM runs Quickbooks. This is stored on a USB flash drive so I can do accounting on any machine, then physically lock up the drive when done. Unless a remote intruder is savvy enough to nail my machine while the VM is active, my Quickbooks data is fairly protected, since when it isn't in use, the external drive is stashed in a safe.
Another VM has Windows
Re: (Score:2)
It can be asserted that running under a user is good enough.
However, the advantage of VM level isolation is that everything related to a project (apps, data, even OS modifications) are stashed in one place. This can be done with users to a limited degree, but being able to have the complete OS with everything needed to run a specific application stored in one place is important. If done right, the VM doesn't care what hardware it runs on, so a future computer that might be ARM but translates x86 opcodes w
Re: (Score:2)
Wow, what browser do you use? You *might* be able to make an argument for netcat being secure, though I sure wouldn't bet on that. Firefox, Chrome, Opera, Safari, and IE have all had vulnerabilities discovered in the last year. Most of them were rapidly patched, and in some cases nobody other than the developers would ever have learned of the vulnerability if not for the patch notes, but I can guarantee you that they didn't find them all!
Also, logging into another account is insufficient. Just as your brows
Re: (Score:2)
Very true, but the burden of proof is on the victim. A PII loss really means nothing to a company other than a couple articles of bad press. Sony came out of the PSN compromise unscathed. Other companies have had break-ins, and they are not the worse for wear for the incidents, regardless of how things are handled.
The only organizations which actually would be held to task for break-ins would be government stuff. A private company losing data is considered normal. A government agency losing the same d
Re: (Score:2, Interesting)
It appears that the hypervisor leaks data from one VM to another by not clearing a cache. If that is all, this leak can be fixed by explicitly clearing the cache when switching to another VM. This will probably cost a few CPU cycles (and cause a few extra cache misses when a VM is resumed).
The problem isn't data leaking but the change in latency to access memory when on the same cpu where a crypto algorithm is running. The keys can be reverse engineered if the crypto algorithm uses a well known table. There is no direct data leakage across VMs required. This is not a joke it is effective, but you have to get you VM onto the same server as the VM you are attacking. You can avoid the issue by using a dedicated server in the Amazon cloud case, or an Extra Large VM in Azure.
Detailed blog post (Score:2, Interesting)
You can find a more detailed blog post about this here:
http://blog.cryptographyengineering.com/2012/10/attack-of-week-cross-vm-timing-attacks.html
Summary of the attack (Score:5, Informative)
This post gives a high-level summary of the attack:
http://blog.cryptographyengineering.com/2012/10/attack-of-week-cross-vm-timing-attacks.html [cryptograp...eering.com]
(I previously posted this as AC, but it vanished.)
Re: (Score:2)
A few factors come to mind:
1. The fact that certain not-officially-known nation states have pulled off highly sophisticated attacks is a matter of public knowledge.
2. A 'nation-state', as an entity that gets to collect taxes and is charged with assorted non-market processes like 'defense', has much broader ability to do things that make minimal financial sense. If you are worried about spammers, or PIN-skimmers, or whatnot it suffices to be more expensive to attack than your resources are worth. If you are
need access to the host on which the vm is running (Score:1)
Easily fixed (Score:2)
Re: (Score:2)
Well, and exclude that processor from ever executing code for other VMs. Remember that a process is an OS-level concept. The OS can certainly set affinity to a single CPU and exclude all other processes from using that CPU, but that only works for intra-OS context switches. When the hypervisor context-switches the execution to a different VM, you get a different OS (that of the attacker) executing on (potentially) the same processor. The attacker's OS has no ability to see, much less reason to respect, the
Not Likely Reproducible in Production Environment (Score:5, Informative)
In other words, this exploit requires: knowing what cryptographic software is being run, the presence of Xen and an apparent security hole therein, and lucky core colocation of the VMs in an environment that could easily have dozens of VMs running against more than a dozen cores "over the course of a few hours".
In short, all of this is unlikely to be reproducible outside of a lab.
Re: (Score:2)
It also appears that it doesn't work if there are more than two virtual machines running on the same physical CPU, or if the attacking VM is the only one running on a given CPU.
With 3 or more VMs on the same CPU, the cache gets populated by virtual machines other than the targeted "victim" machine, so the attacker doesn't know which is affecting what. And if the attacking VM is alone on the CPU, it can't find any other VMs to attack.
Re: (Score:2)
The StuxNet attack vector was probably thought of in the same way - until it was used. When there is a high value target, getting all the ducks in a row is not impossible, it's the reason professionals are called in. You only have to make it work once (though you have to avoid getting caught on all the other attempts).
Re: (Score:2)
this exploit requires: knowing what cryptographic software is being run, the presence of Xen and an apparent security hole therein, and lucky core colocation of the VMs in an environment that could easily have dozens of VMs running against more than a dozen cores "over the course of a few hours".
It doesn't seem that far fetched to me. Call up the cloud provider as a customer and ask what technology they use. If they say Xen, go ahead, if not find another cloud provider.
Then you guess what cryptography sof