用强化学习生成能骗过多个AI文本检测器的改写文本。
StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
- 基于强化学习训练改写策略，兼顾语义保留与多检测器绕过。
- 在15,310条人工/14,656条AI文本上实现97.6%攻击成功率，平均检测率近乎为零。
- 攻击可迁移至未见检测器，暴露检测系统共性漏洞，适合安全评估者使用。
AI文本检测器面临严峻的鲁棒性挑战：对抗性改写攻击可在保持语义一致的同时逃避检测。我们提出StealthRL，一种强化学习框架，用于在真实对抗环境下测试检测器的鲁棒性。StealthRL利用Qwen3-4B模型结合LoRA适配器，通过分组相对策略优化（GRPO）训练改写策略，以复合奖励函数平衡检测规避与语义保真度。我们在全过滤版MAGE测试集（含15,310条人工文本和14,656条AI生成文本）上评估了六种攻击设置（M0-M5），针对四种检测器（RoBERTa、Fast-DetectGPT、Binoculars、MAGE）进行测试。StealthRL在三个检测器上实现接近零检测率，平均TPR@1%FPR为0.024，将平均AUROC从0.79降至0.43，并达到97.6%的攻击成功率。关键发现是攻击可迁移至训练中未见的两个检测器，表明存在共享架构弱点而非检测器特异性脆弱。我们还通过李克特评分对500组样本进行大模型质量评估，分析检测分数分布以解释规避机制，并提供各检测器的AUROC及其自助法置信区间。结果揭示当前AI文本检测系统的显著鲁棒性缺陷，并确立StealthRL作为系统的对抗评估范式。代码与评估流程已公开于https://github.com/suraj-ranganath/StealthRL。
原文摘要 · Abstract (English)
AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a paraphrase policy against a multi-detector ensemble using Group Relative Policy Optimization (GRPO) with LoRA adapters on Qwen3-4B, optimizing a composite reward that balances detector evasion with semantic preservation. We evaluate six attack settings (M0-M5) on the full filtered MAGE test pool (15,310 human / 14,656 AI) against four detectors: RoBERTa, Fast-DetectGPT, Binoculars, and MAGE. StealthRL achieves near-zero detection on three of the four detectors and a 0.024 mean TPR@1%FPR, reducing mean AUROC from 0.79 to 0.43 and attaining a 97.6% attack success rate. Critically, attacks transfer to two held-out detectors not seen during training, revealing shared architectural vulnerabilities rather than detector-specific brittleness. We additionally conduct LLM-based quality evaluation via Likert scoring on 500 matched samples per method, analyze detector score distributions to explain why evasion succeeds, and provide per-detector AUROC with bootstrap confidence intervals. Our results expose significant robustness gaps in current AI-text detection and establish StealthRL as a principled adversarial evaluation protocol. Code and evaluation pipeline are publicly available at https://github.com/suraj-ranganath/StealthRL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。