Tennessee woman held for months after facial recognition error in Fargo case

In short: A Tennessee woman was arrested and held for nearly six months after facial recognition software incorrectly linked her to a North Dakota bank fraud case.

What happened

Fargo police in North Dakota investigated a bank fraud case in spring 2025. Investigators said a suspect used a fake U.S. Army ID to withdraw thousands of dollars, and the person appeared on bank security video.

Police used facial recognition software, which is a tool that compares a face in a photo or video to other images (like a computer trying to match a face the way a person might, but using math). The system flagged Angela Lipps, a 50-year-old woman who lives in Tennessee, as a possible match. A detective then looked at her social media and her driver’s license photo and decided the faces looked similar.

Lipps was charged with four counts of unauthorized use of personal identifying information and four counts of theft. U.S. Marshals arrested her at her home in Tennessee as a North Dakota fugitive. She was held without bail for about four months in Tennessee, then extradited to North Dakota.

Lipps said she had never been to North Dakota. Her lawyer later provided bank records showing she was in Tennessee during the time of the crimes, and she was released. The charges were dismissed without prejudice, meaning prosecutors could file them again.

Fargo Police Chief David Zibolski acknowledged “missteps” but did not apologize, according to recent statements. North Dakota lawmakers and the ACLU have pointed to the case as an example of the risk of false arrests when police rely on facial recognition.

Why it matters

If police treat a computer match as strong proof, an innocent person can lose months of freedom before getting a chance to show the mistake. The case is also raising questions about what checks should be required before an arrest, especially when the person lives far away and says they were never there.

Source: NYTimes