Bit2Watt: How a Regular Cloud Customer Could Wobble the Power Grid

Key points

• Three researchers at Zhejiang University describe a technique called Bit2Watt, accepted to the CHES 2026 hardware-security conference.
• The attack needs no software flaw and no break-in, just a normal paid cloud account with access to a GPU (a specialised chip used for AI and graphics work).
• By running carefully timed workloads, a tenant can force a data centre's power draw to jump up and down fast enough to stress the electrical grid feeding it.
• The paper reports the team measured real power swings on live hardware, not just simulated them.
• The finding reframes cloud abuse as a physical-infrastructure problem, not only a cyber one.

Here is an unusual one. A team at Zhejiang University claims that a regular cloud customer, the kind who pays by the hour for computer time, can rattle the power grid a data centre sits on. No exploit. No stolen password. Just workloads.

They call it Bit2Watt. The paper has been accepted to CHES 2026, the annual hardware-security conference run by the International Association for Cryptologic Research. It is a serious venue, not a stunt.

The short version: rent some GPUs, the specialised chips that power AI training and 3D graphics, then run software that switches between heavy and light work on a precise rhythm. Modern GPUs draw huge amounts of electricity when busy and very little when idle. Flip enough of them together, fast enough, and the whole building's power consumption starts to oscillate like a pendulum.

Do that at the scale of a hyperscale data centre and the swing shows up on the electrical grid outside the fence.

Can a paying customer really shake the grid?

According to the researchers, yes, at least in principle, and they say they have the measurements to back part of it up. The Hacker News, which flagged the paper, notes the evidence comes in two pieces: direct power measurements on real hardware, and modelling of what happens when that pattern is scaled up across a full data hall.

Think of it like everyone in an office block jumping in unison. One person, nothing. A thousand people on the same beat, the floor starts to move. Grids are engineered for smooth, predictable demand. Sudden synchronised spikes and drops are exactly what grid operators dread, because they can trip protection systems designed to prevent blackouts.

What makes Bit2Watt awkward is that nothing about it looks like an attack from a security team's dashboard. The tenant is running their own paid workload on their own rented machines. No malware. No unusual network traffic. No policy broken. It resembles a classic denial-of-service idea, flooding a resource to knock it over, but pointed at the electricity supply instead of a website.

Compare it to a noisy-neighbour problem in cloud computing, where one tenant hogs shared resources and slows others down. Bit2Watt is the same shape of problem, just aimed at the wall socket.

What should ordinary people take from this?

Not panic. This is a research paper, not a live incident. There is no report of anyone using Bit2Watt in the wild, and pulling it off would need serious resources: a lot of rented GPU time, careful coordination, and a target data centre big enough to matter to the grid.

But it is a useful reminder. As AI workloads push data centres to draw as much electricity as small cities, the line between a cyber-attack and an attack on physical infrastructure gets thinner. A cloud bill and a grid disturbance are starting to live in the same conversation.

For cloud providers, the homework is clear. Watch for tenants whose power profile oscillates in suspicious patterns, cap how quickly workloads can ramp up and down at the hardware level, and coordinate with the utilities that feed them. For everyone else, this is a story to file away as evidence that AI's hunger for power is now a security question, not just an environmental one.