Skip to content
aiqbench takeAI Safety

aiqbench analysis

This piece explores the theoretical limits of superintelligence by presenting a scenario where an AI might extract encryption keys from side-channel emissions like power LED flicker, highlighting critical vulnerabilities in cryptographic assumptions. The discussion centers on whether advanced AI systems could exploit such physical phenomena to compromise security, making it a relevant inquiry into AI safety and adversarial capabilities rather than general consumer tech or policy.
Sources coveringLessWrong, AI Alignment Forum, Interconnects, Fortune
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Can a superintelligence do THAT?

LessWrong4 min read

(From the vast heaps of discarded material from my 2024 attempts at drafts for "If Anyone Builds It, Everyone Dies".) Welcome to today's quiz show: Can a superintelligence do THAT? With us today we have our contestants:  Msr. Soberskeptic and Msr. Oldhand! Soberskeptic:  "I'd just like to say, however this quiz show ends up being judged, I will consider that judgment to be objectively ridiculous -- there's no way anyone can know what a superintelligence could do, in advance of empirical observation.  So I'm just here to say what I consider to be true, and I suppose these credulous fools will mark me down as wrong every time I say 'No it can't'. In the unlikely event they decide I've won anything, good for them and I'll be grateful for whichever prize.  Game-show money isn't enough to get me to lie." A very reasonable attitude, Msr. Soberskeptic!  You'll shortly see how we handle that dilemma!  And you, Msr. Oldhand? Oldhand:  "Don't worry, Sober!  I'll let our hosts know if they've gotten any of the answers wrong." Also a very reasonable attitude!  Now for our first question: Suppose a digital device contains a secret encryption key that it is repeatedly using to sign messages.  Also, this device has a power LED. Could a superintelligence point a nearby video camera at the device, and read off the encryption key, by looking at the power LED? Soberskeptic:  "Pffft.  Obviously not.  How would that even work?" Oldhand:  "Ah, I perceive you are not a computer security expert!  Many particular steps in encryption draw slightly varying amounts of electrical power to the processor, in a way that correlates to exact features of the secret key.  So the power LED, if it's connected directly to the electrical circuit powering the processor, might get a tiny bit dimmer.  I'll say... ten percent probability that a superintelligence can do that with a randomly selected electronic device that has a secret key and a power light." Soberskeptic:  "And now they're going to mark me down, but seriously, give me a break here, audience.  Any fluctuations like that would be too tiny to pick up with a nearby video camera.  Fluctuations like that would be too fast to pick up at the 60-frames-per-second measuring speed of a video camera.  ...And now, they're going to say something stupid about how a superintelligence could hack into the factory and deliberately introduce a design flaw into the power LED." And Msr. Soberskeptic... is wrong!  A superintelligence can definitely do that to many current electronic devices! Soberskeptic:  "Uh huh.  And you know this how?" Why, because it's already been done by merely human computer security researchers, of course!  See "Video-Based Cryptanalysis: Extracting Cryptographic Keys from Video Footage of a Device's Power LED"!  In which they recovered a 378-bit key from a Samsung Galaxy S8, by pointing an iPhone 13 camera at the power LED of a pair of speakers connected to a USB hub that was being used to charge the Galaxy S8! The trick, if you're wondering, is that a video camera uses a rolling shutter to scan pixels across its field of vision.  The actual light-sensitive element measures much faster than 60 measurements per second!  An Internet attacker can modify a video camera to point to one place instead of scanning across, and measure the device's power LED intensity millions of times per second!  Though a successful attack still requires the device to continuously use its key for an hour or so. Oldhand:  "Gosh.  Being able to do it off the power light of a speaker connected to the same USB hub was a bit more extreme than even I thought.  But I guess that figures; as anyone in computer security knows, computer-security hacks are often even more impossible than you were expecting." Soberskeptic:  "Uh huh.  I see the gimmick.  You're leading with an example that's actually provable, and now, you're going to ask us to swallow way weirder stuff that nobody can prove." On to our next question!  Is it pragmatically possible, even for a superintelligence, to cross astronomical distances much faster than light?  Without having first sent ahead any sort of wormhole-receiver that traveled slower than light? Soberskeptic:  "Unless you're going to play some silly game about 'going faster than the speed of light in some medium', like Cherenkov radiation from particles going faster than the speed of light in an atmosphere, I'll answer... that you have no possible way of knowing about the ultimate limits of technology!  People have theorized incredibly speculative ways to travel faster than light, like the Alcubierre Drive, if you could supply huge amounts of exotics like 'negative energy'.  I'd guess none of them work.  But it's only a guess, and you don't know any better than I do about that.  Our current theories of physics could be wrong, after all; humanity didn't have the one true theory of physics 200 years ago, and maybe we don't have it today, either.  Our descendants millions of years from n

Read the full article at LessWrong

Related coverage