mlsanityData to 14 Oct 2026

RADAR: Robust AI-Text Detection via Adversarial Learning

arXiv 2307.03838 ↗First posted 7 Jul 2023cs.CL cs.AI cs.LGcited by 190

Not on the map. Why?

Abstract (arXiv)

Recent advances in large language models (LLMs) and the intensifying popularity of ChatGPT-like applications have blurred the boundary of high-quality text generation between humans and machines. However, in addition to the anticipated revolutionary changes to our technology and society, the difficulty of distinguishing LLM-generated texts (AI-text) from human-generated texts poses new challenges of misuse and fairness, such as fake content generation, plagiarism, and false accusations of innocent writers. While existing works show that current AI-text detectors are not robust to LLM-based paraphrasing, this paper aims to bridge this gap by proposing a new framework called RADAR, which jointly trains a robust AI-text detector via adversarial learning. RADAR is based on adversarial training of a paraphraser and a detector. The paraphraser's goal is to generate realistic content to evade AI-text detection. RADAR uses the feedback from the detector to update the paraphraser, and vice versa. Evaluated with 8 different LLMs (Pythia, Dolly 2.0, Palmyra, Camel, GPT-J, Dolly 1.0, LLaMA, and Vicuna) across 4 datasets, experimental results show that RADAR significantly outperforms existing AI-text detection methods, especially when paraphrasing is in place. We also identify the strong transferability of RADAR from instruction-tuned LLMs to other LLMs, and evaluate the improved capability of RADAR via GPT-3.5-Turbo.

Key facts. Cited by 190 papers in the map (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 7 Jul 2023.

Builds on

28 of 37 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  8. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  9. 2023A Watermark for Large Language Modelscited by 725
  10. 2019Defending Against Neural Fake Newscited by 559
  11. 2019Release Strategies and the Social Impacts of Language Modelscited by 513
  12. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 496
16 more
  1. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 429
  2. 2023Can AI-Generated Text be Reliably Detected?cited by 386
  3. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 376
  4. 2019Automatic Detection of Generated Text is Easiest when Humans are Fooledcited by 261
  5. 2023GPT detectors are biased against non-native English writerscited by 178
  6. 2018Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examplescited by 94
  7. 2023On the Possibilities of AI-Generated Text Detectioncited by 88
  8. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  9. 2018DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Textcited by 40
  10. 2018Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classificationcited by 35
  11. 2019Training language GANs from Scratchcited by 31
  12. 2021Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Modelcited by 30
  13. 2020TextGAIL: Generative Adversarial Imitation Learning for Text Generationcited by 28
  14. 2021Factorising Meaning and Form for Intent-Preserving Paraphrasingcited by 22
  15. 2022Hierarchical Sketch Induction for Paraphrase Generationcited by 22
  16. 2023Adversarial Transformer Language Models for Contextual Commonsense Inferencecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 46; 2025: 65; 2026: 71.

190 papers.

Sort:

By area:

  1. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 263
  2. 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviewscited by 164
  3. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 163
  4. 2024Mapping the Increasing Use of LLMs in Scientific Paperscited by 118
  5. 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 105
  6. 2024Watermark Stealing in Large Language Modelscited by 92
  7. 2023OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examplescited by 80
  8. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76
  9. 2023A Survey on Detection of LLMs-Generated Contentcited by 71
  10. 2023An Unforgeable Publicly Verifiable Watermark for Large Language Modelscited by 65
  11. 2025DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressivelycited by 63
  12. 2024DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learningcited by 53
38 more
  1. 2024SoK: Watermarking for AI-Generated Contentcited by 51
  2. 2024M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detectioncited by 43
  3. 2025People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated textcited by 40
  4. 2025Are You Getting What You Pay For? Auditing Model Substitution in LLM APIscited by 38
  5. 2023Towards Possibilities & Impossibilities of AI-generated Text Detection: A Surveycited by 28
  6. 2024Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmerscited by 27
  7. 2024Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attackcited by 27
  8. 2024Beemo: Benchmark of Expert-edited Machine-generated Outputscited by 27
  9. 2023From Text to Source: Results in Detecting Large Language Model-Generated Contentcited by 26
  10. 2024Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attackscited by 26
  11. 2023A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Textscited by 23
  12. 2024Detecting AI-Generated Text: Factors Influencing Detectability with Current Methodscited by 23
  13. 2024Permute-and-Flip: An optimally stable and watermarkable decoder for LLMscited by 22
  14. 2025AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guaranteescited by 21
  15. 2025DAMAGE: Detecting Adversarially Modified AI Generated Textcited by 20
  16. 2025Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writingcited by 19
  17. 2024The Impact of Large Language Models in Academia: from Writing to Speakingcited by 18
  18. 2025Rethinking Data Protection in the (Generative) Artificial Intelligence Eracited by 18
  19. 2025Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Textcited by 17
  20. 2024Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Textcited by 16
  21. 2025HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoringcited by 15
  22. 2025Machine-generated text detection prevents language model collapsecited by 14
  23. 2025Which Contributions Deserve Credit? Perceptions of Attribution in Human-AI Co-Creationcited by 14
  24. 2024EAGLE: A Domain Generalization Framework for AI-generated Text Detectioncited by 13
  25. 2025GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. Humancited by 13
  26. 2024Real-time Factuality Assessment from Adversarial Feedbackcited by 12
  27. 2025DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learningcited by 12
  28. 2024Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Bettercited by 11
  29. 2024Duwak: Dual Watermarks in Large Language Modelscited by 11
  30. 2024A Practical Examination of AI-Generated Text Detectors for Large Language Modelscited by 11
  31. 2025DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigmcited by 11
  32. 2026GPTZero: Robust Detection of LLM-Generated Textscited by 11
  33. 2024Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitationscited by 10
  34. 2024On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writingcited by 10
  35. 2025Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Predictioncited by 10
  36. 2025Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectorscited by 10
  37. 2026Detecting LLM-Generated Text with Performance Guaranteescited by 10
  38. 2025Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectorscited by 9

50 most cited of 190 All 190 (JSON)