[2506.07001] Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Computation and Language

arXiv:2506.07001 (cs)

[Submitted on 8 Jun 2025 (v1), last revised 29 Oct 2025 (this version, v2)]

Title:Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

Authors:Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi, Shoumik Saha, Soheil Feizi<br>View a PDF of the paper titled Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text, by Yize Cheng and 4 other authors

View PDF<br>HTML (experimental)

Abstract:The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated text detectors have been proposed to mitigate these risks, many remain vulnerable to simple evasion techniques such as paraphrasing. However, recent detectors have shown greater robustness against such basic attacks. In this work, we introduce Adversarial Paraphrasing, a training-free attack framework that universally humanizes any AI-generated text to evade detection more effectively. Our approach leverages an off-the-shelf instruction-following LLM to paraphrase AI-generated content under the guidance of an AI text detector, producing adversarial examples that are specifically optimized to bypass detection. Extensive experiments show that our attack is both broadly effective and highly transferable across several detection systems. For instance, compared to simple paraphrasing attack--which, ironically, increases the true positive at 1% false positive (T@1%F) by 8.57% on RADAR and 15.03% on Fast-DetectGPT--adversarial paraphrasing, guided by OpenAI-RoBERTa-Large, reduces T@1%F by 64.49% on RADAR and a striking 98.96% on Fast-DetectGPT. Across a diverse set of detectors--including neural network-based, watermark-based, and zero-shot approaches--our attack achieves an average T@1%F reduction of 87.88% under the guidance of OpenAI-RoBERTa-Large. We also analyze the tradeoff between text quality and attack success to find that our method can significantly reduce detection rates, with mostly a slight degradation in text quality. Our adversarial setup highlights the need for more robust and resilient detection strategies in the light of increasingly sophisticated evasion techniques.

Comments:<br>NeurIPS 2025

Subjects:

Computation and Language (cs.CL)

Cite as:<br>arXiv:2506.07001 [cs.CL]

(or<br>arXiv:2506.07001v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2506.07001

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yize Cheng [view email]<br>[v1]<br>Sun, 8 Jun 2025 05:15:01 UTC (594 KB)

[v2]<br>Wed, 29 Oct 2025 19:16:47 UTC (607 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text, by Yize Cheng and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2025-06

Change to browse by:

cs

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors...