Comment by niftich | Hacker News Reader

Comment by niftich | Hacker News Reader

This post lifts out the key parts of the paper [1] and is a good summary. I think the paper is an accessible read as well.

Not too much discussion two weeks ago when the paper was posted on HN [2], so I will raise a point I've made before [3][4][5] and is consistent with the recommendations of the paper (and another post in this thread [6]): this is an opportunity to improve the terminology, mental models, and formalisms of observable state, and its implications for information hiding, privilege separation, and computer system design.

This conversation needs not only to occur among (e.g.) computer chip designers and cryptography experts, but also among higher-stack users of that technology, so that the information leakage aspects and trade-offs can be analyzed together with other performance indicators of the system.

It seems as if the haphazard, ad hoc way that chipmakers and system architects dealt with this issue have contributed to an environment where Spectre could occur: and such timing attacks were never a secret, but resistance to them in various levels of mainstream computing appears to have been fitted in a patchwork of hasty fixes and well-meaning but informal caution. The conversation around this topic could use an upgrade, and the paper's authors agree.

[1] https://ts.data61.csiro.au/publications/csiroabstracts/Ge_YC... [2] https://news.ycombinator.com/item?id=19547293 [3] https://news.ycombinator.com/item?id=17308014 [4] https://news.ycombinator.com/item?id=16165942 [5] https://news.ycombinator.com/item?id=19644997 [6] https://news.ycombinator.com/item?id=19670296

You might even say there's room for a startup to reinvent computers (and operating systems) from the ground up.

Would you?

With about a hundred billion dollars of funding and a ten years to market schedule, maybe?

I don't know if I'd look at it with that lens. Clearly, knowledge and analyses of this topic are resident in academia and have been long present at various levels of industry, but other factors like performance and power consumption have received generous affordances by hardware designers, and makers of system software and application software had to step in where the hardware provided little help for leak-proof sharing. In retrospect, the market may have rewarded hardware makers' direction of pursuit -- until now, but the survivors of those past pursuits remain.

Leak-proof sharing of resources may be a more marketable pursuit now, with cloud providers hosting code from mutually untrusted parties, and consumers running delivered applications and untrusted Javascript on the same machine, but I'd rather see the conversation about this topic improve across the board, independent from commercial forces.

Not until the people who are building existing systems become (financially / legally) liable for their mistakes. Homogeneity is fragile, but it's also extremely cheap, which is how we got here.

Do you think that people in the software field need something like the AMA to protect us so that we can have liability?

Well let's think it through. It would seemingly have to follow the Disruptive Technology arc. That means it would start off as a crappy computer that had really great information leakage control. And it would be marketed to a small but enthusiastic market who really values that, and doesn't mind that most everything else is a PITA.

Who might that market be?

Major cloud companies and VM providers?

Most of these vulnerabilities come from speculative execution impacting a shared cache.

Nah, cloud providers are under enornlis pressure to optimize resource usage (real estate, electricity, labor). A hardware design without competitive performance has a snowball's chance in hell of being adopted in that space. The economics of cloud datancenter mean that security only needs to be good enough, not perfect.

In that case, the perception that current hardware security is good enough needs to change.

Or the cloud vendors could start offering compute running on new, more secure hardware - e.g. special VM types marketed accordingly.

I think that this is wishful thinking on your part unless the drastic performance per power drops are negated.

I personally think that these performance drops leads to a horrific environmental impact because every performance drop means that more hardware needs to be provisioned and powered to counter it. So this directly results in more toxic waste from these elecronics and a higher carbon dioxide output into the atmosphere (cloud data centers are a major consumer of electricity). Compared to the long term impact of that, a extra few security breaches sound like the lesser evil to me personally.

Major cloud companies == energy consumption. Most of the time cloud users would be able to 'just' rent the entire machines and not have to bother with 'untrusted' code.

Yeah, this is sounding like a good angle to start with. Target users are people who need to squeeze as much performance out of hardware as they can without leaking information while running untrusted code. So, cloud providers seems like exactly where to start.

Cloud providers who target security-sensitive users who also don't have a lot of money (to just pad the hardware budget) would be ideal.

Cryptocurrency users?

(Although they tend to be very bad at threat modelling)

Yeah, that's a good starting point. Maybe not just cryptocurrency users, but "people who have expensive digital assets on a computer that runs untrusted code".

Although, it kind of seems like, the more expensive you digital assets, the more you just need to a) hire a full time security person and b) insure your asset.

I'm not sure how a new OS would fit into that.

It seems like it would have to be people WITHOUT a lot of assets who would be the initial customers. People who can't just pay a security person to go over their images.

So maybe casual crypto users.

But wouldn't they be better off just with a custom dongle? A dongle isn't running untrusted software.

Also, isn't part of this technology that it squeezes a little more performance out of a machine without leaking information?

That takes me to the comment below... cloud hosting platforms.

You'd have to be fast. HP is on it:

https://www.digitalartsonline.co.uk/news/creative-hardware/h...

https://www.theregister.co.uk/2013/11/01/hp_memristor_2018/

4 more years till that 2013 plan reaches the 10 year threshold.

Reply on news.ycombinator.com