StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

Abstract

AI-text detectors are increasingly used in high-stakes settings, but their robustness to meaning-preserving adversarial rewriting remains unclear. We introduce StealthRL, a reinforcement learning framework for stress-testing detectors with adaptive paraphrase attacks. StealthRL trains a paraphrase policy against a detector ensemble while enforcing semantic fidelity, then evaluates transfer to held-out detector families on the full filtered MAGE test pool. Across RoBERTa, Fast-DetectGPT, Binoculars, and MAGE, the resulting attack sharply degrades detection performance, driving mean TPR@1%FPR down to 0.024 while retaining nontrivial semantic overlap and readable prose. The attack also transfers to detectors not used during training, indicating a broader robustness failure rather than overfitting to a single target model. We complement the main results with detector-score analysis, repeated-generation stability checks, and automatic and judge-based quality evaluation. Our findings suggest that current AI-text detectors remain brittle under adaptive paraphrasing pressure and motivate robustness evaluation at deployment-relevant operating points. Our code and the trained model checkpoint are publicly available.