Robustness of Machine-Generated Text Detection

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 47

All topics

Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
May 28, 2026Zhihao Wu, Gracia Gong, Qinglin Zhu +2Watermark Removal LLM Watermarking
Department of Informatics, King’s College London, UK · Department of Mathematics, Imperial College London, UK · Department of Statistics, University of Warwick, UK.
Base Models Look Human To AI Detectors
May 19, 2026Yixuan Even Xu, Ziqian Zhong, Aditi Raghunathan +2AI-Generated Text Detection Language Model Generation Evaluation
Carnegie Mellon University
DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection
May 15, 2026Junchao Wu, Yefeng Liu, Chenyu Zhu +8Multilingual Language Model Evaluation AI-Generated Text Detection
NLP2CT Lab, Department of Computer and Information Science, University of Macau · Alibaba Group · Xiamen University
Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods
May 14, 2026Andrii Shportko, Inessa VerbitskyAI-Generated Text Detection Robustness of Machine-Generated Text Detection
Northwestern University · Evanston, IL, USA
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
May 12, 2026Tom Sander, Hongyan Chang, Tomáš Souček +10Language Model Fingerprinting LLM Watermarking
FAIR, Meta Superintelligence Labs
MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text
May 7, 2026Chenjun Li, Cheng Wan, Johannes C. PaetzoldAI-Generated Text Detection Domain Generalization
Cornell University, Ithaca, NY 14853, USA · Weill Cornell Medicine, New York, NY 10021, USA · Cornell Tech, New York, NY 10044, USA
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
May 6, 2026Mohd Ruhul Ameen, Akif Islam, Nadim Mahmud +1Diffusion Model Watermarking Watermark Removal
College of Engineering and Computer Science, Marshall University, Huntington, WV, USA · Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh · Miami University, Oxford, OH 45056, USA
Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators
May 5, 2026Mohamed Mady, Johannes Reschke, Björn SchullerAI-Generated Text Detection Transformer
Chair of Health Informatics, Technical University of Munich (TUM), Germany · OTH Regensburg, Germany · GLAM – Group on Language, Audio & Music, Imperial College London, United Kingdom
Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms Race
May 4, 2026Andreas Maier, Moritz Zaiss, Siming BayerAI-Generated Text Detection Language Model Generation Evaluation
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Institute of Neuroradiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training
May 4, 2026Wenjing Duan, Qi Zhou, Yuanfan LiAdversarial Training AI-Generated Text Detection
Faculty of Electronic and Information Engineering, Xi’an Jiaotong University
Beyond Perplexity: Character Distribution Signatures and the MDTA Benchmark for AI Text Detection
May 3, 2026Priyadarshan Narayanasamy, Swastik Agrawal, Klint Faber +1AI-Generated Text Detection Robustness of Machine-Generated Text Detection
Department of Computer Science, University of Maryland, College Park
StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer
Apr 30, 2026Guantian ZhengFlow Matching AI-Generated Text Detection
DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis
Apr 29, 2026Siyuan Li, Aodu Wulianghai, Guangyan Li +5AI-Generated Text Detection LLM Security
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, Shanghai, China · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors
Apr 28, 2026Yuanfan Li, Qi Zhou, Chengzhengxu Li +5AI-Generated Text Detection Language Model Generation Evaluation
Faculty of Electronic and Information Engineering, Xi’an Jiaotong University · Queen Mary University of London
Spotlights and Blindspots: Evaluating Machine-Generated Text Detection
Apr 17, 2026Kevin Stowe, Kailash PatilAI-Generated Text Detection Language Model Generation Evaluation
Pindrop
Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence
Oct 8, 2025Shuangyi Chen, Ashish KhistiAI-Generated Text Detection Language Model Robustness
Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada.
VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text
Sep 30, 2025Trieu Hai Nguyen, Sivaswamy AkileshAI-Generated Text Detection Language Model Robustness
Faculty of Information Technology, Nha Trang University, 02 Nguyen Dinh Chieu Street, North Nha Trang 57100, Vietnam · Faculty of Business Administration, Swiss School of Business and Management Geneva, 12 Avenue des Morgines, Geneva 1213, Switzerland

May 28, 2026, cs.CLJ/K move · Enter open · S save

Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

Zhihao Wu, Gracia Gong, Qinglin Zhu, Yudong Chen+1

Department of Informatics, King’s College London, UK · Department of Mathematics, Imperial College London, UK · Department of Statistics, University of Warwick, UK.

Watermark Removal LLM Watermarking Robust Watermarking Language Model Ensembles Robustness of Machine-Generated Text Detection

Open paper AskPDF arXiv

Watermarking embeds statistical signatures in AI-generated text for detection and attribution. We reveal a fundamental vulnerability: when users access multiple models (today's reality), watermarks trivially fail. Watermarks perturb output distributions away from the original, and in competitive markets, these perturbations are typically independent across providers. We theoretically prove that averaging output probability distributions recovers the unwatermarked distribution with up to a second-order error term. Empirically, simply averaging 3-5 models cancels out these perturbations. We introduce WASH (Watermark Attenuation via Statistical Hybridisation), which solves practical challenges in ensemble generation: vocabulary misalignment and tokenisation differences across heterogeneous models. Experiments across six watermarking schemes and three LLMs show that averaging across 3 models suppresses detection z-scores from 5-300 to below 2 (below the detection threshold of 4) and reduces TPR at 5% FPR to below 50%, while improving quality by 27.5% and running 6 times faster than the best baseline on the long sequence generation. Our results suggest that robust AI-text detection via watermarking requires either accepting this fundamental vulnerability or unprecedented coordination among model providers.

Momentum

Related topics

Latest papers 47