Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2606.00392 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910273594458112 |
|---|---|
| author | Wang, Mingyi Shen, Zhuoer Bu, Yuheng Zou, Shaofeng |
| author_facet | Wang, Mingyi Shen, Zhuoer Bu, Yuheng Zou, Shaofeng |
| contents | AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservation. In particular, optimizing directly for detector evasion can degrade fine-grained semantics, whereas scalarized reward designs provide only indirect, weight-sensitive control over the evasion-semantics trade-off. We address this limitation by formulating detector-evasive LLM paraphrasing as a Constrained Markov Decision Process, where detector evasion is the primary objective and semantic preservation is enforced as an explicit constraint. We propose Detector Evasion Policy Optimization (DEPO), a Lagrangian primal-dual reinforcement learning algorithm with a novel GRPO-style group-based policy update. DEPO adaptively balances semantic preservation and detector evasion during training, enabling the policy to improve attack success within a prescribed semantic-preservation region. Experiments on MAGE, M4, RAID, and peer-review datasets, evaluated against MAGE, RoBERTa, RADAR, Binoculars, and Fast-DetectGPT detectors, show that DEPO achieves strong detector evasion while precisely satisfying the semantic preservation constraint. DEPO also exhibits cross-domain, cross-detector, and prompt-level robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00392 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization Wang, Mingyi Shen, Zhuoer Bu, Yuheng Zou, Shaofeng Machine Learning Artificial Intelligence AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservation. In particular, optimizing directly for detector evasion can degrade fine-grained semantics, whereas scalarized reward designs provide only indirect, weight-sensitive control over the evasion-semantics trade-off. We address this limitation by formulating detector-evasive LLM paraphrasing as a Constrained Markov Decision Process, where detector evasion is the primary objective and semantic preservation is enforced as an explicit constraint. We propose Detector Evasion Policy Optimization (DEPO), a Lagrangian primal-dual reinforcement learning algorithm with a novel GRPO-style group-based policy update. DEPO adaptively balances semantic preservation and detector evasion during training, enabling the policy to improve attack success within a prescribed semantic-preservation region. Experiments on MAGE, M4, RAID, and peer-review datasets, evaluated against MAGE, RoBERTa, RADAR, Binoculars, and Fast-DetectGPT detectors, show that DEPO achieves strong detector evasion while precisely satisfying the semantic preservation constraint. DEPO also exhibits cross-domain, cross-detector, and prompt-level robustness. |
| title | Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2606.00392 |