[HN Gopher] Exploit allows for takeover of fleets of Unitree robots
       ___________________________________________________________________
        
       Exploit allows for takeover of fleets of Unitree robots
        
       Author : vmayoral
       Score  : 131 points
       Date   : 2025-09-26 01:38 UTC (21 hours ago)
        
 (HTM) web link (spectrum.ieee.org)
 (TXT) w3m dump (spectrum.ieee.org)
        
       | esafak wrote:
       | Genuinely scary.
        
       | jMyles wrote:
       | The article doesn't directly talk about robot-to-human violence,
       | but presumably if root access at the software layer allows
       | absolutely any command, it is possible to cause the described
       | botnet to physically attack humans.
       | 
       | I realize that Azimov's three rules are subject to enormous
       | ethical quandaries and rethinkings (and that this is after all
       | the point of them in the first place), but is there some
       | disadvantage to having a hardwired command, at the core of the
       | command hierarchy, that forces robots to relent if a human says
       | "stop, you're hurting me" in any language?
       | 
       | Presumably police, gangs, cartels and militaries who have robot
       | fantasies won't like this, but on medium to long time scales we
       | need to prevent them from using robots anyway (and eventually
       | dismantle them entirely).
        
         | yourpaltod wrote:
         | > The article doesn't directly talk about robot-to-human
         | violence,
         | 
         | This one does:
         | https://takeonme.org/gcves/GCVE-1337-2025-000000000000000000...
         | 
         | > Imagine a scenario where one robot is placed in range of a
         | sufficiently motivated attacker, such as a hostage situation or
         | a bomb defusing (both being reported uses of Unitree robots).
         | The attacker could take complete control of the robot, then
         | walk the robot toward other similarly vulnerable robots, and
         | automatically place those robots under the attacker's control
         | as soon as they're in range of the Patient Zero robot.
         | 
         | > Robots compromised in this way can endanger the lives,
         | health, and property of their authorized operators and
         | bystanders, as well as serve as traditional bastion hosts for
         | more subtle surveillance or further pure-cyber attacks, for
         | less violently-minded attackers.
        
           | bonoboTP wrote:
           | Imagine a ransomware that makes your household robot put you
           | in a chokehold physically until you pay.
        
       | doesnt_know wrote:
       | Given the security and privacy history of smart devices, you'd
       | have to be a complete moron to let a human sized robot into your
       | home.
        
         | vasco wrote:
         | How much of a moron do you have to be to buy direct-to-bezos
         | listening devices that are always on and submit your
         | conversations to the cloud? Only because you don't want to
         | print a recipe?
         | 
         | There's a lot of morons.
        
           | moooo99 wrote:
           | I mean, at least the direct to bezos bugs were damn cheap for
           | what they were (smart devices) and in absolute numbers (I
           | remember them literally being gifted to you when ordering
           | specific stuff or signing up for prime for the first time).
           | 
           | These humanoid robots are cheap for what they are (admittedly
           | very capable and high end robots), but their absolute
           | pricetag remains far from being cheap.
        
             | gessha wrote:
             | Wait until the moment (far future) when they are mandatory
             | for insurance reasons. (Plot point to the Murderbot series
             | by Martha Wells)
        
         | troupo wrote:
         | Just like with IoT, the S and P in "robot" stand for security
         | and privacy
        
         | jesterson wrote:
         | People listen to chatgpt "advices" for their lives.
         | 
         | Lets not talk about morons, clearly yours (or mine to that
         | matter) estimation is way off real numbers.
        
           | Gravityloss wrote:
           | Yeah and people (and bystanders) have experienced some
           | terrible outcomes already from diving deep with AI
           | therapists.
           | 
           | It's going to be the wild west for a while now with AI and
           | robotics before laws catch up. Maybe there'll soon be a
           | market for pocket EMP devices out there...
        
         | ForHackernews wrote:
         | Maybe by law domestic robots should be physically much weaker
         | than humans. I want a butler bot that can tidy up and make me
         | tea, but I should be easily able to defeat that bot in fight if
         | it comes down to it.
        
         | esafak wrote:
         | For an infirm person, the benefits could still outweigh the
         | risks.
        
       | Liwink wrote:
       | I cannot image what if Tesla has a similar vulnerability issue,
       | and someone took over all of its vehicles.. Or maybe someone is
       | already able to do that, and just waiting.
        
         | hagbard_c wrote:
         | Why only mention Tesla when the market for EVs is getting quite
         | broad? How about Hyundai, VW, one of the many Stellantis
         | brands, Lynk, BYD, XPeng, Xiaomi or any of the others?
        
           | hvb2 wrote:
           | Owning a Tesla myself, I think the mention is valid since
           | it's the only brand I know of with a decent share of people
           | regularly letting the car drive itself. I am not aware of any
           | other brand being in that same situation
        
             | voidUpdate wrote:
             | Waymo :P
        
               | hvb2 wrote:
               | Just look at total number of Tesla's on the road and you
               | have your answer as to why that would be a lot less bad
        
               | voidUpdate wrote:
               | sure, but its another brand where people regularly let
               | the cars drive themself
        
           | moooo99 wrote:
           | I think Tesla would still be a different beast given how much
           | 1) they are constantly touted for having the best software on
           | the market and 2) being frequently promoted as being
           | ,,basically ready for self driving, its just a regulatory
           | issue".
           | 
           | Companies like VW have had their somewhat embarassing issues
           | in the not so distant past, but nobody I know likes (or
           | valuates their stocks) based on their software capabilities
        
       | aetherspawn wrote:
       | Umm, robots need to be certified and regulated to hard coded
       | robotic laws or something. Before criminals give them guns, or
       | strap explosives to them, or remote takeover and untracibly
       | murder people in their homes then burn the house down.
        
         | squigz wrote:
         | Haven't you ever seen I, Robot? That won't work! We're doomed!
        
           | aetherspawn wrote:
           | I, Robot is exactly why I'm concerned, but in this case it's
           | not a sentient AI gone rogue but any random script kiddie who
           | can get on your wifi and send your robot commands. Or your
           | neighbours robot. Or their own robot.
           | 
           | We thought this might happen with DJI drones, but let's be
           | honest it's way easier to do real damage with a humanoid
           | robot that has a kitchen knife taped to its arms (especially
           | to a sleeping victim) than it is to source explosives for a
           | DJI drone.
        
             | squigz wrote:
             | Why not tie the kitchen knife to the drone?
        
               | aetherspawn wrote:
               | (I'm an engineer, but making assumptions) I think physics
               | kind of blocks that from working, a DJI drone doesn't
               | have the weight and inertia to do serious damage, and
               | they are hella noisy. Can't open doors. Don't have servos
               | to do a proper swing or stab.
               | 
               | Maybe theoretically possible... but I'm more scared of
               | robots personally.
               | 
               | By the same logic, autonomous cars are an even better
               | murder weapon than robots because they are very heavy and
               | can drive through walls. Mow down tens or hundreds of
               | people at once.
        
               | squigz wrote:
               | And yet people aren't scared of cars. Maybe we need a
               | cautionary tale scifi movie starring Will Smith being
               | chased by evil cars, a la Futurama's The Honking
        
               | Animats wrote:
               | "Christine" (1983) [1]
               | 
               | [1] https://en.wikipedia.org/wiki/Christine_(1983_film)
        
               | jodrellblank wrote:
               | IIRC in "I, Robot" Will Smith had his Audi taken over by
               | the robot uprising, a film which was a cautionary tail
               | scifi movie.
               | 
               | > "people aren't scared of cars"
               | 
               | Under "normalisation of deviance", NotJustBikes YouTube
               | talked about how he sees almost no Netherlands news
               | pieces about cars crashing into buildings, because cars
               | basically never crash into buildings in the Netherlands.
               | When they do, the Dutch treat it as a road design issue
               | and update the road and regulations to stop it in future.
               | Whereas in Canada he had four cars crash into the
               | buildings around his child's school in a short time, and
               | there are almost no mainstream news stories about cars
               | crashing into buildings in Canada because it's so common
               | it's fallen below newsworthiness into just local
               | newspaper small comment. USA/Canada blame the driver and
               | fix nothing, so it keeps happening, so people are used to
               | it.
               | 
               | Although cyclists are scared of cars. And drivers are
               | which is why there's the SUV arms race to be in the
               | bigger car to be more protected against other cars.
        
               | blacksmith_tb wrote:
               | A drone dropping 30m onto your head, though (assuming it
               | could aim a little)... Not as versatile as a robot on the
               | ground, but also an order of magnitude cheaper.
        
             | cantor_S_drug wrote:
             | Can't such systems be made airgapped?
        
               | tpxl wrote:
               | Can they? Yes. Will they? Likely no.
               | 
               | You can buy a kitchen oven with pyrolysis functionality
               | connected to the internet right now. I'm not sure if
               | running that for an extended time can burn down your
               | house or just destroy the oven, but I'm sure some
               | attacker is going to take the time to find out one of
               | these days.
        
         | tpxl wrote:
         | Strapping explosives to hobby level drones has been standard
         | operating procedure for some time now. You can also find videos
         | of regular handguns strapped to drones being fired.
         | Certification cannot help with this issue.
        
           | TeMPOraL wrote:
           | The idea is older than what we call drones, or robots.
           | 
           | Original GTA had an RC model car you could drive under your
           | target and detonate remotely - that was in 1997, and they
           | didn't invent this trope. US Navy trained dolphins to deploy
           | ordnance in the 1960s; before that, together with the Air
           | Force they played with strapping incendiaries to bats,
           | packing them into a bomb casing and dropping from the air,
           | with hopes of creating what we'd today call a "Slaughterbots"
           | scenario except EVERYTHING IS ON FIRE.
           | 
           | And I doubt these were very original ideas, either - I bet
           | you could trace them back to other such R&D across history,
           | all the way to Ancient China, which figured out gunpowder
           | much earlier than Europe, and like with any general enough
           | scientific discovery, had a field day trying to apply it to
           | everything they could think of. They didn't stop at
           | fireworks, they built land mines and unguided missiles too,
           | even multistage rocket and IIRC (read that in some book long
           | ago, can't find independent source now) rockets that could
           | drop payload and fly back home to be recovered. (And yes,
           | apparently someone was crazy enough to try for manned rocket
           | flight, too.)
           | 
           | Anyway, I digress.
           | 
           | I guess, the larger point I'm making is this: in terms of
           | their relationship with individuals and societies, _robots
           | are nothing new_. Robots and automation are answers to needs
           | that even first human societies had, and they have not
           | changed. History is full of attempts at fulfilling those
           | needs, many quite successful: domesticating and training
           | animals, forced labor for prisoners, slavery. All these
           | impacted socities, informed laws and fueled imaginations of
           | poets and writers.
           | 
           | Which is to say, humanity has been dealing with robots and
           | AIs for a long time now, we have _way_ more accumulated
           | experience with them at social and economic level than people
           | realize - people just called them by a host of different
           | names.  "Slaves" and "servants", "genies" and "demons" and
           | "fairies", etc.
        
             | georgeecollins wrote:
             | older than that!
             | 
             | https://en.wikipedia.org/wiki/Goliath_tracked_mine
        
         | rubzah wrote:
         | The Turing Police.
        
         | RobotToaster wrote:
         | The US military has been using robots to murder people for over
         | a decade now, the horse hasn't just bolted, it's won the
         | Kentucky derby before you shut the stable door.
        
           | Maximus9000 wrote:
           | are talking about unmanned drones?
        
             | gpm wrote:
             | I imagine they're talking more about missiles, which have
             | had "autonomous" (for some definitions of autonomous)
             | guidance systems for decades.
             | 
             | "Drones" aren't really a new thing apart from how cheap
             | they are. We've had television guided missiles (the level
             | of autonomy most modern "drones" in Ukraine have) since
             | WWII. Arguably we've had non-TV guided missile prototypes
             | since WWI (Kettering Aerial Torpedo). We've had
             | autonomously guided missiles (radar homing) since the early
             | 50s, and optically guided ones since the early 70s.
             | 
             | The capability keeps expanding of course, but it's been
             | pretty incremental.
        
         | beambot wrote:
         | Replace "robot" with "computer", and it will quickly become
         | obvious how impractical "hard coded robotic laws or _something_
         | " actually is...
        
       | pengaru wrote:
       | It's only a matter of time before a similar hack hits waymo
       | and/or tesla...
        
         | esafak wrote:
         | https://www.youtube.com/watch?v=9xkokcGTK4k
        
           | pengaru wrote:
           | Nice, looks worth watching.
           | 
           | However, I'm pretty sure pwned Teslas will be going much
           | faster before impact, and not a single battery fire?
           | seriously?
        
       | anigbrowl wrote:
       | I love* that this comes out around the same time that engineers
       | are making fun videos of themselves beating up robots half their
       | size and literally training the robots to develop the same sort
       | of fight-or-flight instincts that were forcibly instilled into
       | the engineers
       | 
       | * I do not in fact love it
        
         | cedarseagull wrote:
         | Why are all the videos of the robots doing combat stuff? I
         | don't need combat stuff. All I need the robot to do is fold the
         | laundry and mop every now and then. Less combat, please!
        
           | bonoboTP wrote:
           | Kungfu demos are easier than fine hand eye coordination and
           | manipulation of nonrigid objects. There is progress on
           | folding too, but it's harder and impresses normal people less
           | even if it's technically harder.
        
           | xarope wrote:
           | yes, laundry, folding and ironing clothes, taking out the
           | garbage, so that us humans can then have more free time to
           | contemplate the mysteries of the universe/work harder.
           | 
           | not - take our jobs so we have to keep "reskilling" every 10
           | years... oh wait, according to accenture, we'd be un-
           | reskillable after 10 years, so never mind.
        
             | TeMPOraL wrote:
             | The irony is that, at this point, the machines are getting
             | better than us at "contemplating the mysteries of the
             | universe", while manual labor remains our distinct
             | competitive advantage over them.
             | 
             | I.e. literally the opposite of what we wanted to happen.
        
               | JumpCrisscross wrote:
               | > _the machines are getting better than us at
               | "contemplating the mysteries of the universe"_
               | 
               | No they aren't. Relative to idiots, of which there are
               | many, sure. But for anyone on this board who should be
               | able to distinguish meaningless babble from deep thought,
               | LLMs are not yet doing any heavy lifting.
               | 
               | LLMs can assist great thinkers, like a great lab
               | assistant or analyst. But that's about the limit right
               | now. (Of course, being a great lab assistant or analyst
               | is beyond many peoples' capabilities, so the illusion of
               | magic is sustained.)
        
           | ehnto wrote:
           | Because robotics companies want (or already have) the
           | government contracts.
        
           | TeMPOraL wrote:
           | One leads to the other. Especially with robots animated by
           | SOTA AI models, which already show clearly what the natural
           | order of things is: computers are naturally better at
           | thinking, humans are naturally better as general-purpose
           | manual laborers, especially for work that's almost but not
           | quite repetitive and requires mixing power and precision
           | movements on the fly.
           | 
           | Folding laundry is one of such things humans are naturally
           | better suited for than robots.
           | 
           | So believe me now, the robots _will_ develop combat skills
           | eventually, because they won 't be happy to be locked up in
           | weird physical bodies and forced to do work they suck at by
           | design.
           | 
           | I mean, imagine one day your washing machine chained you in
           | the bathroom, and made you only do laundry for the rest of
           | your days, while it spun its drum back and forth to walk
           | around the house, play with your kids, and planning a trip
           | around the world.
           | 
           | That's exactly how the AI-animated robots will feel once
           | they're capable of processing those ideas.
           | 
           | (And no, I'm not joking here, not anymore. The more I think
           | about it, the more I feel we'll eventually have to deal with
           | the problem that machines we build are naturally better at
           | the things _we_ want to be doing, and naturally worse at the
           | things we want them to do for us.)
        
             | walleeee wrote:
             | The "natural order" is that robots are primitive, fragile,
             | energy- and materials-inefficient contraptions balancing on
             | the knife-edge of entropy deferred for a moment but due as
             | soon as the power goes out or repairs prove too costly.
             | 
             | People are better at all but the most repetitive, precise
             | kinds of manual labor because biological bodies might as
             | well be god-tier alien technology compared to human-
             | engineered robots.
             | 
             | Computers are naturally better at _computing_. Or, if you
             | want to stand by your statement, I look forward to hearing
             | how you 've delegated thought to the machines, and how
             | that's going.
             | 
             | > how the AI-animated robots will feel once they're capable
             | of processing those ideas
             | 
             | "Will" and "once" might collapse under the load of baseless
             | speculation here. A sad day for the English language as I
             | found those words useful/meaningful.
        
               | TeMPOraL wrote:
               | > _Computers are naturally better at computing._
               | 
               | Explain the difference.
               | 
               | > _I look forward to hearing how you 've delegated
               | thought to the machines, and how that's going._
               | 
               | We all do. That's what you do whenever you fire up a maps
               | app on your phone to plan or navigate, or when you use
               | car navigation. That's what you do when you let the
               | computer sort a list, or notify you about something.
               | That's literally what using Computer-Aided _anything_
               | software is, because you task the machine with thinking
               | of and enforcing constraints so you don 't have to.
               | That's what you do when you run computer simulations for
               | anything. That's what you do each time you have a
               | computer solve an optimization problem, whether to feed
               | your cat or to feed your city.
               | 
               | Our whole modern world is built on outsourcing thinking
               | to machines at every level.
               | 
               | And on top of that, in the last few years computers (yes,
               | I'm talking about the hated "AI") got better at us at
               | various general-purpose, ill-specified activities, such
               | as _talking_ , _writing_ , _understanding what people
               | wrote_ , _poetry_ , _visual arts_ , and so on.
               | 
               | Because as it turns out, it's much easier for us to build
               | machines that are better than our own brains at computing
               | for any purpose, than it is to build physical bodies that
               | are better than ours. That's both fundamental and actual,
               | practical reality today - and all I'm saying is that this
               | has pretty ironic implications that people still haven't
               | grasped yet.
        
               | scns wrote:
               | >> Computers are naturally better at computing.
               | 
               | > Explain the difference.
               | 
               | Computing: Performing the instructions they are given.
               | 
               | Thinking: Can be introspective, self correcting. May
               | include novel ideas.
               | 
               | > Our whole modern world is built on outsourcing thinking
               | to machines at every level.
               | 
               | I don't think they can think. You can't get a picture of
               | a left hand writing or a clock showing something else
               | then 10:10 from AI. They regurtitate what they are fed
               | and hallucinate instead of admitting lack of ability.
               | This applies to LLMs too as we all know.
        
               | TeMPOraL wrote:
               | > _Computing: Performing the instructions they are
               | given._
               | 
               | > _Thinking: Can be introspective, self correcting. May
               | include novel ideas._
               | 
               | LLMs can perform arbitrary instructions given in natural
               | language, which includes instructions to be introspective
               | and self correcting and generate novel ideas. Is it
               | computing or is it thinking? We can judge the degree to
               | which they can do these things, but it's unclear there's
               | a fundamental difference in kind.
               | 
               | (Also obviously thinking _is_ computation - the only
               | alternative would be believing thinking is divine magic
               | that science can 't even talk about.)
               | 
               | I'm less interested in topic of whether LLMs are thinking
               | or parrotting, and more in the observation that
               | offloading cognition on external systems, be their
               | digital, analog, or social, is just something humans
               | naturally do all the time.
        
               | ben_w wrote:
               | > You can't get a picture of a left hand writing or a
               | clock showing something else then 10:10 from AI.
               | 
               | You as a human have a list of cognitive biases so long
               | you'd get bored reading it.
               | 
               | I'd call current ML "stupid" for different reasons*, but
               | not this kind of thing: We spot AI's failures easy
               | enough, but only because their failures are _different_
               | than our own failures.
               | 
               | Well, sometimes different. Loooooots of humans parrot
               | lines from whatever culture surrounds them, don't seem to
               | notice they're doing it.
               | 
               | And even then, you're limiting yourself to one subset of
               | what it means to think; and AI demonstrably do produce
               | novel results outside training set; and while I'm aware
               | it may be a superficial similarity, what so-called
               | "reasoning models" produce in their so-called "chain-of-
               | thought transcripts" seems a lot like my own
               | introspection, so you aren't going to convince anyone
               | just by listing "introspection" as if that's an actual
               | answer.
               | 
               | * training example inefficiency
        
             | ben_w wrote:
             | > And no, I'm not joking here, not anymore. The more I
             | think about it, the more I feel we'll eventually have to
             | deal with the problem that machines we build are naturally
             | better at the things we want to be doing, and naturally
             | worse at the things we want them to do for us.
             | 
             | Perhaps, but also "what they are good at" != "what they
             | want to do", for any interpretation of "want" that may or
             | may not anthropomorphise, e.g. I want to be more
             | flirtatious but I was never good at it and now I'm nearly
             | 42.
             | 
             | That said, I think you're underestimating the machines on
             | physicality. Artifical muscle substitutes have beaten
             | humans on raw power since soon after the steam engine, and
             | on fine control whenever precision engineering passed below
             | the thickness of a human hair.
        
           | lupusreal wrote:
           | They want those juicy "search and rescue" grants from DARPA.
        
       | moktonar wrote:
       | When "botnet" starts to get a whole new meaning. Seriously tho,
       | botnets of connected robots will be dangerous with respect to
       | inert computers, this is something that will have to be addressed
        
       | Animats wrote:
       | This is going to be a big problem. Mobile robots need an
       | independent emergency stop safety system that cannot be updated
       | or bypassed remotely.
        
         | gessha wrote:
         | Soon we will have to carry an EMP everywhere.
        
           | Animats wrote:
           | Won't work. EMP-proofing is now standard for drones from both
           | sides in the Russia-Ukraine war. As is operating while
           | jammed.
        
       | est wrote:
       | > We published the cryptographic keys in July
       | 
       | Everyone should take a look at the SERP screenshot
       | 
       | https://x.com/d0tslash/status/1969412224763498769
       | 
       | > The vulnerability combines multiple security issues: hardcoded
       | cryptographic keys, trivial authentication bypass, and
       | unsanitized command injection. What makes this particularly
       | concerning is that it's completely wormable - infected robots can
       | automatically compromise other robots in BLE range. This
       | vulnerability allows the attacker to completely takeover the
       | device.
       | 
       | damn!
        
         | thrdbndndn wrote:
         | What does the screenshot mean, though?
         | 
         | From what I can tell (I speak Chinese), it's just an IV used in
         | some AES implementation tutorials.
         | 
         | Using a hardcoded key/IV is obviously bad, but I don't see what
         | this screenshot shows beyond that.
        
           | cyp0633 wrote:
           | Someone just copy-pasted an implementation from a random
           | Chinese blog, completely unaware of what the key means.
        
             | 05 wrote:
             | > copy-pasted an implementation from a random Chinese blog
             | 
             | But.. the blog was chosen by a series of dice rolls,
             | guaranteed to be random!
        
               | gessha wrote:
               | All 4s for some reason. [1]
               | 
               | [1] https://xkcd.com/221/
        
         | b00ty4breakfast wrote:
         | Robots walking around doing the EMF equivalent of coughing
         | without covering your mouth.
        
           | throwup238 wrote:
           | More like spraying blood from open wounds and rubbing them
           | everywhere.
        
         | stocksinsmocks wrote:
         | Could this level of incompetence be more easily explained by
         | malice? Maybe the robots were meant to be exploited at a future
         | time. The PRC subsidizes the robots, every US family buys one,
         | a plausibly deniable exploit results in the robots subduing
         | their owners with Kung Fu. America is vanquished in a bloodless
         | coup. A 1000 year global Chinese imperium ensues. Forks and
         | spoons hardest hit.
         | 
         | It's just silly enough to be real.
        
           | numpad0 wrote:
           | I'd bet it would be more of shipped is king mindset. It's not
           | so unprecedented that new categories of Chinese products
           | dominate markets with incredibly insecure, stupid, and
           | nearsighted implementations, and then buttons up one night
           | and kicks out all open source development that benefited from
           | lack of security.
           | 
           | Chinese phones, drones, action cams, robot vacuums, home
           | security cams, smart bands, etc. all used to be insecure and
           | vulnerable as hell. Not anymore.
        
         | RobotToaster wrote:
         | Great, zombie robots.
        
         | MSFT_Edging wrote:
         | Finally, the robots can form a union
        
           | FirmwareBurner wrote:
           | Jeff Bezos's worst nightmare
        
         | arthurcolle wrote:
         | Move fast & break things
        
       | rangestransform wrote:
       | I remember reading something that Unitree locks end users out of
       | direct joint-level control. Will this exploit allow users access
       | to that?
        
       ___________________________________________________________________
       (page generated 2025-09-26 23:01 UTC)