New FICS Study
Commercial AI Text Detectors Lack Robustness for High-Stakes Environments
Recent reports claim that artificial intelligence-generated text (AIGT) is flooding academic literature. However, a new study by FICS Research reveals that the commercial tools used to detect AIGT are unreliable, easily circumvented, and poorly suited for academic adjudication.
FICS Researchers also found that with a simple tweak to the LLM, the detectors were rendered basically useless, incapable of distinguishing AIGT from human-generated text.
“These current tools are not reliable or robust enough to use to measure the problem. We really can’t use them to adjudicate these decisions. People’s careers are on the line here.” —Patrick Traynor, Ph.D., professor and interim chair of the University of Florida Department of Computer & Information Science & Engineering
The study, “AI Wrote My Paper and All I Got Was This False Negative: Measuring the Efficacy of Commercial AI Text Detectors,” will be presented this week at the 2026 IEEE Symposium on Security and Privacy. The paper is co-authored by FICS researchers Seth Layton, Ph.D., Bernardo B. P. Medeiros and FICS Director Kevin Butler, and Patrick Traynor.