mlsanityData to 7 Oct 2026

Attacking Neural Text Detectors

arXiv 2002.11768 ↗First posted 19 Feb 2020cs.CR cs.CLcited by 37

Not on the map. Why?

Abstract (arXiv)

Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these language models. This paper presents two classes of black-box attacks on these detectors, one which randomly replaces characters with homoglyphs, and the other a simple scheme to purposefully misspell words. The homoglyph and misspelling attacks decrease a popular neural text detector's recall on neural text from 97.44% to 0.26% and 22.68%, respectively. Results also indicate that the attacks are transferable to other neural text detectors.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 11; 2024: 13; 2025: 1; 2026: 5.

37 papers.

Sort:

By area:

  1. 2023A Watermark for Large Language Modelscited by 667
  2. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  3. 2023Provable Robust Watermarking for AI-Generated Textcited by 259
  4. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 255
  5. 2023On the Reliability of Watermarks for Large Language Modelscited by 170
  6. 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviewscited by 160
  7. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 157
  8. 2024Mapping the Increasing Use of LLMs in Scientific Paperscited by 112
  9. 2022Do Language Models Plagiarize?cited by 72
  10. 2023Watermarking Text Generated by Black-Box Language Modelscited by 68
  11. 2022Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspectivecited by 40
  12. 2024Securing Large Language Models: Threats, Vulnerabilities and Responsible Practicescited by 36
25 more
  1. 2024Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Modelscited by 30
  2. 2023Towards Possibilities & Impossibilities of AI-generated Text Detection: A Surveycited by 28
  3. 2022Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformerscited by 25
  4. 2023WatME: Towards Lossless Watermarking Through Lexical Redundancycited by 22
  5. 2022A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publicationscited by 18
  6. 2024Permute-and-Flip: An optimally stable and watermarkable decoder for LLMscited by 17
  7. 2024Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Textcited by 14
  8. 2022SynSciPass: detecting appropriate uses of scientific text generationcited by 10
  9. 2023Mutation-Based Adversarial Attacks on Neural Text Detectorscited by 9
  10. 2023Stochastic Parrots Looking for Stochastic Parrots: LLMs are Easy to Fine-Tune and Hard to Detect with other LLMscited by 8
  11. 2024'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviewscited by 8
  12. 2023Dual Use Concerns of Generative AI and Large Language Modelscited by 6
  13. 2024ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detectioncited by 6
  14. 2024Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detectioncited by 6
  15. 2025Diversity Boosts AI-Generated Text Detectioncited by 6
  16. 2022Synthetic Text Detection: Systemic Literature Reviewcited by 2
  17. 2024Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attackscited by 2
  18. 2026Detecting the Machine: A Comprehensive Benchmark of AI-Generated Text Detectors Across Architectures, Domains, and Adversarial Conditionscited by 2
  19. 2022A Mutation-based Text Generation for Adversarial Machine Learning Applicationscited by 1
  20. 2024Benchmarking of LLM Detection: Comparing Two Competing Approachescited by 1
  21. 2026Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarkingcited by 1
  22. 2026MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Textcited by 1
  23. 2023Studying the impacts of pre-training using ChatGPT-generated text on downstream taskscited by 0
  24. 2026Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problemscited by 0
  25. 2026CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarkingcited by 0