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

arXiv:2602.08934 · cs.LG, cs.AI, cs.CR · Submitted 2026-02-09 · Read on arXiv

cs.LG, cs.AI, cs.CR

Submitted: 2026-02-09

Updated: 2026-10-23

Terminology

• Robustness — 3× in this paper · explained in 6 episodes
• AUROC — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 10 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Semantic Preservation — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks