Cover Image

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Hao, Kong, Jiawei, Zhuang, Tianqu, Qiu, Yixiang, Gao, Kuofeng, Chen, Bin, Xia, Shu-Tao, Wang, Yaowei, Zhang, Min
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization
by: Fang, Hao, et al.
Published: (2026)

Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective
by: Fang, Hao, et al.
Published: (2026)

Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
by: Yu, Hongyao, et al.
Published: (2024)

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
by: Qiu, Yixiang, et al.
Published: (2024)

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
by: Kong, Jiawei, et al.
Published: (2025)

Mitigating Paraphrase Attacks on Machine-Text Detectors via Paraphrase Inversion
by: Soto, Rafael Rivera, et al.
Published: (2024)

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
by: Fang, Hao, et al.
Published: (2025)

PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks
by: Zha, Yiwei, et al.
Published: (2025)

ICAS: Detecting Training Data from Autoregressive Image Generative Models
by: Yu, Hongyao, et al.
Published: (2025)

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
by: Fang, Hao, et al.
Published: (2025)

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
by: Ranganath, Suraj, et al.
Published: (2026)

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
by: Fang, Hao, et al.
Published: (2024)

A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks
by: Qiu, Yixiang, et al.
Published: (2024)

Your Classifier Can Be Secretly a Likelihood-Based OOD Detector
by: Burapacheep, Jirayu, et al.
Published: (2024)

Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated
by: Yang, Muli, et al.
Published: (2026)

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP
by: Kong, Jiawei, et al.
Published: (2025)

Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
by: Cheng, Yize, et al.
Published: (2025)

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations
by: Liu, Haitong, et al.
Published: (2025)

Denial-of-Service Poisoning Attacks against Large Language Models
by: Gao, Kuofeng, et al.
Published: (2024)

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
by: Fang, Hao, et al.
Published: (2024)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
by: Bai, Jiawang, et al.
Published: (2023)

Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models
by: Gao, Kuofeng, et al.
Published: (2025)

EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts
by: Han, Yucheng, et al.
Published: (2024)

Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
by: Li, Jinmin, et al.
Published: (2024)

Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
by: Qiu, Yixiang, et al.
Published: (2025)

Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection
by: Lau, Hiu Ting, et al.
Published: (2024)

Paraphrasing Adversarial Attack on LLM-as-a-Reviewer
by: Kaneko, Masahiro
Published: (2026)

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
by: Wang, Mingyi, et al.
Published: (2026)

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
by: Sun, Shuoyang, et al.
Published: (2026)

FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs
by: Li, Jinmin, et al.
Published: (2024)

Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing
by: Chen, Bin, et al.
Published: (2024)

TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
by: Jo, Sanghyun, et al.
Published: (2025)

Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
by: Wu, Yunshu, et al.
Published: (2024)

Preference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator
by: Chen, Zhuotong, et al.
Published: (2025)

Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods
by: Shportko, Andrii, et al.
Published: (2026)

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
by: Yang, Sheng, et al.
Published: (2024)

RedacBench: Can AI Erase Your Secrets?
by: Jeon, Hyunjun, et al.
Published: (2026)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
by: Wang, Tianchun, et al.
Published: (2024)

The Erosion of LLM Signatures: Can We Still Distinguish Human and LLM-Generated Scientific Ideas After Iterative Paraphrasing?
by: Shahriar, Sadat, et al.
Published: (2025)

Robust Multi-bit Text Watermark with LLM-based Paraphrasers
by: Xu, Xiaojun, et al.
Published: (2024)