mlsanityData to 7 Oct 2026

Mutation-Based Adversarial Attacks on Neural Text Detectors

arXiv 2302.05794 ↗First posted 11 Feb 2023cs.CR cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Neural text detectors aim to decide the characteristics that distinguish neural (machine-generated) from human texts. To challenge such detectors, adversarial attacks can alter the statistical characteristics of the generated text, making the detection task more and more difficult. Inspired by the advances of mutation analysis in software development and testing, in this paper, we propose character- and word-based mutation operators for generating adversarial samples to attack state-of-the-art natural text detectors. This falls under white-box adversarial attacks. In such attacks, attackers have access to the original text and create mutation instances based on this original text. The ultimate goal is to confuse machine learning models and classifiers and decrease their prediction accuracy.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 11 Feb 2023.

Builds on

32 of 48 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  10. 2019When Does Label Smoothing Help?cited by 985
  11. 2016Adversarial Machine Learning at Scalecited by 934
  12. 2014Show and Tell: A Neural Image Caption Generatorcited by 877
20 more
  1. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  2. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 490
  3. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  4. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  5. 2019On the Detection of Digital Face Manipulationcited by 259
  6. 2020Automatic Detection of Machine Generated Text: A Critical Surveycited by 160
  7. 2019FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signalscited by 143
  8. 2020A Survey of Knowledge-Enhanced Text Generationcited by 119
  9. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
  10. 2018Tensor2Tensor for Neural Machine Translationcited by 85
  11. 2019Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detectioncited by 50
  12. 2020Attacking Neural Text Detectorscited by 37
  13. 2020Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classificationcited by 37
  14. 2016Generating Chinese Classical Poems with RNN Encoder-Decodercited by 16
  15. 2020ScriptWriter: Narrative-Guided Script Generationcited by 15
  16. 2020Defense-PointNet: Protecting PointNet Against Adversarial Attackscited by 13
  17. 2022Revisiting Near/Remote Sensing with Geospatial Attentioncited by 12
  18. 2021Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactionscited by 8
  19. 2021Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directionscited by 4
  20. 2020Attention Beam: An Image Captioning Approachcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 4.

9 papers.

  1. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 157
  2. 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 101
  3. 2023J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated Newscited by 10
  4. 2025DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domainscited by 9
  5. 2025GenAI Content Detection Task 3: Cross-Domain Machine-Generated Text Detection Challengecited by 7
  6. 2025Diversity Boosts AI-Generated Text Detectioncited by 6
  7. 2025A Training-free Method for LLM Text Attributioncited by 4
  8. 2023Efficient Black-Box Adversarial Attacks on Neural Text Detectorscited by 3
  9. 2024Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectorscited by 2