Annepaka Yadagiri

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations

2025 · arXiv (Cornell University)

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial attacks, with paraphrasing standing …