Skip to main content
  1. Home
  2. Emerging Tech
  3. News

Misplaced gold nanoparticles could reveal if your 3D printer was hacked

Add as a preferred source on Google

3D printing is still such a new technology that most of us are still wrapping our heads around its numerous possibilities, but we’re not worrying about all the ways that a 3D printer may be susceptible to hackers. Thankfully, researchers are thinking about those kinds of questions — and scientists from Rutgers University and the Georgia Institute of Technology may even have an answer to it.

As it turns out, hacking a 3D printer could lead to all kinds of problems. As Christian Bayens, a researcher on the project from Georgia Tech, told Digital Trends: “A hacker could sabotage a larger manufacturing process by printing parts that would fail prematurely when in use. Outside of that, he or she may want to sit in the system quietly to acquire intellectual property to sell later.”

Recommended Videos

To counter this threat, what the Rutgers and Georgia Tech researchers have developed is a smart sensor-based system that uses multiple methods to check your 3D printer is performing as you’d want it to. The system could be retrofitted into existing printers, and the relatively low cost of the sensors involved means that it would also be affordable.

Image used with permission by copyright holder

It uses three separate safeguards to search for intruders. For starters, the system looks for changes in the printer’s sound, which may be an indicator that malicious software has been installed. Secondly, it searches for anomalies in the movement of the printer’s extruder and other components, meaning divergences from the consistent mechanical path they would normally follow. Finally — and most inventively — the system injects tiny gold nanoparticles into the printer’s filament to make sure that, when an object has been printed, these are distributed as would be expected. (These gold nanoparticles aren’t visible to the naked eye, and have been tested to ensure they don’t have a detrimental impact on a 3D-printed object’s integrity, either.)

If a 3D printed object passes all three tests, researchers are confident that it means your printer has not been hacked. If it fails one (or even all three!) it means you may well have a security problem on your hands.

Currently the system is in the research stage, and is not yet something that’s available for customers to buy. However, the researchers are working to expand it and turn it into something that will be available to the masses. The research was presented this week at the USENIX Security Symposium in Vancouver. A paper describing the project can be read here.

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
The Apple Car may be dead, but it became the foundation of Apple Intelligence
A decade of work on a canceled car project reportedly laid the groundwork for Apple Intelligence.
Apple Intelligence in Apple Car

The Apple Car may have never left the garage, but it apparently gave birth to Apple's AI ambitions. According to Bloomberg's Mark Gurman, Apple's canceled autonomous vehicle project, one that consumed more than a decade of work and over $10 billion before being scrapped in 2024, ended up laying the technological foundation for Apple Intelligence. In a rather ironic twist, one of Apple's most expensive failures may also become one of its most important long-term investments.

The Apple Car forced Apple to think like an AI company

Read more
Researchers hid a prompt injection inside a PNG, and AI fell for it
Hacker

AI coding assistants like Claude are becoming every developer's favorite coworker. They can review code, explain confusing functions, and even write entire features with a single prompt. But new research suggests that this growing trust could also become their biggest weakness.

A team of security researchers (professor Sudipta Chattopadhyay and researcher Murali Ediga) has demonstrated an unusual attack that doesn't target the AI model directly. Instead, it targets what the AI doesn't pay enough attention to during code reviews. Rather than hiding malicious instructions in lines of code, the researchers tucked them inside an image file. Since many AI review tools treat images as decorative assets rather than as something worth inspecting, the pull request can appear perfectly harmless and sail through the review.

Read more
AI has already fallen into the wrong hands and they’re using it to make bombs
Logo, Text

Artificial intelligence has quickly become the go-to tool for everything from writing emails and summarizing meetings to helping students study or developers debug code. But the same technology that saves people time can also be misused, and a new report suggests that terrorist organizations are finding ways to do exactly that.

According to a research paper shared with The New York Times ahead of its publication, researchers found evidence that members of Boko Haram have been using popular AI chatbots to support both day-to-day activities and combat-related tasks. Interviews with 27 former members conducted in Nigeria over the past two years suggest that tools such as ChatGPT, Gemini, Claude, Grok, Meta AI, and DeepSeek were used to gather technical information, troubleshoot weapons, and even assist with planning attacks.

Read more