AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection

ArXi:2606.00016v1 Announce Type: cross Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that rely on surface statistics or likelihood-based signals. We propose \textsc{AEyeDE}, an attribution-driven approach to human-AI authorship detection that leverages model attention as a discriminative signal.