mlsanityData to 7 Oct 2026

Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation

arXiv 2203.01677 ↗First posted 3 Mar 2022cs.CL cs.CR cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have been made to detect adversarial examples. However, detecting adversarial examples may be crucial for automated tasks (e.g. review sentiment analysis) that wish to amass information about a certain population and additionally be a step towards a robust defense system. To this end, we release a dataset for four popular attack methods on four datasets and four models to encourage further research in this field. Along with it, we propose a competitive baseline based on density estimation that has the highest AUC on 29 out of 30 dataset-attack-model combinations. Source code is available in https://github.com/anoymous92874838/text-adv-detection.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

25 of 46 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  5. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  6. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  7. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  9. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
  10. 2018Universal Sentence Encodercited by 485
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  12. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
13 more
  1. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  2. 2017On Detecting Adversarial Perturbationscited by 232
  3. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  4. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 162
  5. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 138
  6. 2020Reevaluating Adversarial Examples in Natural Languagecited by 83
  7. 2020Robust Encodings: A Framework for Combating Adversarial Typoscited by 58
  8. 2019Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classificationcited by 55
  9. 2020Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examplescited by 54
  10. 2021Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrificecited by 30
  11. 2017Minimum Covariance Determinant and Extensionscited by 18
  12. 2021BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attackscited by 17
  13. 2020A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attackscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 11; 2024: 7; 2025: 8; 2026: 1.

32 papers.

Sort:

By area:

  1. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  2. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
  3. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  4. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  5. 2024Calibrating Large Language Models with Sample Consistencycited by 72
  6. 2024API Is Enough: Conformal Prediction for Large Language Models Without Logit-Accesscited by 68
  7. 2024A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMscited by 35
  8. 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 32
  9. 2023Query-Efficient Black-Box Red Teaming via Bayesian Optimizationcited by 31
  10. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  11. 2024Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planningcited by 16
  12. 2025HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detectioncited by 13
20 more
  1. 2023Verifying the Robustness of Automatic Credibility Assessmentcited by 8
  2. 2025Uncertainty-aware abstention in medical diagnosis based on medical textscited by 6
  3. 2022Are Synonym Substitution Attacks Really Synonym Substitution Attacks?cited by 4
  4. 2025Taming Object Hallucinations with Verified Atomic Confidence Estimationcited by 4
  5. 2023Toward Stronger Textual Attack Detectorscited by 3
  6. 2023Efficient Black-Box Adversarial Attacks on Neural Text Detectorscited by 3
  7. 2024Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?cited by 3
  8. 2025Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Modelscited by 3
  9. 2025Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Searchcited by 3
  10. 2022ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimationcited by 2
  11. 2023On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detectioncited by 2
  12. 2025CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignmentcited by 2
  13. 2025Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removalcited by 2
  14. 2022Understanding, Detecting, and Separating Out-of-Distribution Samples and Adversarial Samples in Text Classificationcited by 1
  15. 2022On deceiving malware classification with section injectioncited by 1
  16. 2023Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classificationcited by 1
  17. 2025ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMscited by 1
  18. 2023VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformationscited by 0
  19. 2024Adversarial Attacks and Dimensionality in Text Classifierscited by 0
  20. 2026Evaluating the Relevance of Uncertainty Estimators for LLM Hallucinationcited by 0