RESEARCH DEMO
SRL
StealthRL
AI-text detectors are increasingly used in high-stakes settings, yet their robustness to meaning-preserving adversarial rewriting remains uncertain. StealthRL is an RL framework for stress-testing AI-text detectors with adaptive paraphrase attacks. StealthRL trains a paraphrase policy against a detector ensemble while preserving semantic content, then evaluates transfer to held-out detector families.
Research preview.
Do not paste private text. Outputs are for robustness exploration, not detector-evasion guarantees.
Output
StealthRL rewrite
Your paraphrase will appear here after the request completes.
Input words-
Output words-
Edit rate-
Latency-
Copy output and open:
Show original text
Run the demo to compare source and rewritten text.
Was this rewrite useful?