mlsanityData to 7 Oct 2026

Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks

arXiv 2606.31074 ↗First posted 30 Jun 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the adversarial RAID. This framework marks a pioneering effort in statistical methods to enhance detection reliability against attacks. We release our data and code at https://github.com/baoguangsheng/triospect.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 74 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

41 of 74 references.

References · 41

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  5. 2018Hierarchical Neural Story Generationcited by 1,182
  6. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  7. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  8. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  9. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  10. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  11. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 490
  12. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 472
29 more
  1. 2018Generating Natural Language Adversarial Examplescited by 422
  2. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  3. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  4. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  5. 2023Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvaturecited by 278
  6. 2019Automatic Detection of Generated Text is Easiest when Humans are Fooledcited by 260
  7. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 255
  8. 2023DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Textcited by 207
  9. 2023RADAR: Robust AI-Text Detection via Adversarial Learningcited by 187
  10. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 157
  11. 2023MAGE: Machine-generated Text Detection in the Wildcited by 130
  12. 2023DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Textcited by 127
  13. 2020TweepFake: about Detecting Deepfake Tweetscited by 117
  14. 2019Real or Fake? Learning to Discriminate Machine from Human Generated Textcited by 98
  15. 2023Protecting Language Generation Models via Invisible Watermarkingcited by 81
  16. 2021Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasurescited by 69
  17. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  18. 2024Raidar: geneRative AI Detection viA Rewritingcited by 51
  19. 2021Disentangling Syntax and Semantics in the Brain with Deep Networkscited by 39
  20. 2019A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representationscited by 37
  21. 2024Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attackcited by 27
  22. 2024Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attackscited by 25
  23. 2024Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihoodcited by 24
  24. 2024Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detectioncited by 23
  25. 2025DAMAGE: Detecting Adversarially Modified AI Generated Textcited by 20
  26. 2021Detecting Fake News Using Machine Learning : A Systematic Literature Reviewcited by 19
  27. 2023How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attackscited by 18
  28. 2024Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Bettercited by 11
  29. 2025DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigmcited by 10

Built on by

Not cited yet.