Standard WiFi can identify individuals with near-perfect accuracy

jackson-mcd2 pts0 comments

Privacy: Any Wi-Fi can now identify you with near perfect accuracy - Digital Journal

Connect with us

Hi, what are you looking for?

Image: © PhotoTelegram

Image: © PhotoTelegram

Researchers report how ordinary Wi-Fi routers may soon be able to secretly recognize and track people with near-perfect accuracy. Is this something of societal benefit or a further extension of state surveillance of its citizens?

Scientists at the Karlsruher Institut für Technologie (Germany) have demonstrated a new form of surveillance: identifying people using nothing more than ordinary Wi-Fi signals.

By analysing how radio waves bounce around a room, researchers can effectively “see” and recognise individuals. This is even when they are not carrying a device and even when their phone is turned off.

The process

By observing the propagation of radio waves, researchers can create an image of the surroundings and of persons who are present.

This process works similar to a normal camera, the difference being that radio waves, instead of light waves, are used for the recognition.

Devices on a wireless network regularly send feedback data known as beamforming feedback information (BFI) to the router. Since this information is transmitted without encryption, anyone within range can potentially read it.

The researchers say these signal reflections can effectively create multiple "views" of a person, allowing AI systems to learn and recognise individual identities.

How this technology works in practice

A device (like a radar, Wi‑Fi transmitter, or specialised sensor) sends out radio frequency (RF) waves into an environment.

The waves spread out through walls, furniture, and air. Unlike visible light, radio waves can penetrate many materials.

When radio waves encounter objects, they:

Reflect off surfaces (walls, bodies, furniture)

Scatter in multiple directions

Absorb partially , depending on material

Humans are particularly detectable because the body contains water which creates a strong radio frequency interaction. Furthermore, the human body, as it moves, creates signal changes as with variations in breathing rates.

These signals carry information about:

Distance (from time delay)

Shape and size (from signal distortion)

Movement (from frequency shifts, e.g., Doppler effect)

Using advanced algorithms (often AI or statistical models), researchers analyse the signals to reconstruct an image or map.

AI extract features such as:

Position of objects,

Movement patterns,

Presence of people (even through walls).

This process is similar to how radar detects aircraft, with the added advantage of advanced AI.

Avoiding detection?

Turning off your smartphone is not enough to avoid detection. According to the researchers, nearby wireless devices connected to the network still generate enough signal activity for the system to work.

Taking this a stage further, the technology could transform everyday routers into quiet monitoring systems that operate without attracting attention.

Passing by a café that operates a Wi-Fi network, an individual could be identified without noticing it and be recognised later. This could be something exploited by public authorities or companies.

A problem that will soon be everywhere

If the technology is harnessed, detection will be inescapable for most people. Wi-Fi networks pose a unique concern because they are nearly everywhere (homes, offices, restaurants, airports, and public spaces across the world) and remain largely invisible.

In tests involving 197 participants, the researchers said the system identified individuals with nearly 100% accuracy. The recognition remained effective regardless of viewing angle or how the participants walked.

Countering the threat

To reduce the consequences of this potential threat to a person’s liberty, the researchers are calling for stronger privacy protections and safeguards to be included in the upcoming IEEE 802.11bf Wi-Fi standard.

The research appears in CCS ’25: Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, titled “BFId: Identity Inference Attacks Utilizing Beamforming Feedback Information.”

In this article:Detection, Location, Privacy, Radar, Tracking, wi-fi

Written By<br>Dr. Tim Sandle

Dr. Tim Sandle is Digital Journal's Editor-at-Large for science news.<br>Tim specializes in science, technology, environmental, business, and health journalism. He is additionally a practising microbiologist; and an author. He is also interested in history, politics and current affairs.

Advertisement

Subscribe to our newsletter

Trending

Business

Day two at Upper Bound pushes AI from theory to practice across industry, government, and talent

Business

Upper Bound speakers urge Canada to hold on to its AI advantage

Business

Canada and CIFAR names 42 new and renewed AI research chairs in $24M talent bet

Business

Banker: AI will replace ‘lower-value human capital’

Business

California governor orders a plan to...

researchers waves radio business accuracy image

Related Articles