mlsanityData to 14 Oct 2026

What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples

arXiv 2309.10916 ↗First posted 19 Sep 2023cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial examples, deliberately crafted using small perturbations to fool deep neural networks, were first studied in image processing and more recently in NLP. While approaches to detecting adversarial examples in NLP have largely relied on search over input perturbations, image processing has seen a range of techniques that aim to characterise adversarial subspaces over the learned representations. In this paper, we adapt two such approaches to NLP, one based on nearest neighbors and influence functions and one on Mahalanobis distances. The former in particular produces a state-of-the-art detector when compared against several strong baselines; moreover, the novel use of influence functions provides insight into how the nature of adversarial example subspaces in NLP relate to those in image processing, and also how they differ depending on the kind of NLP task.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 61 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

41 of 61 references.

References · 41

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2016Pointer Sentinel Mixture Modelscited by 3,096
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  8. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  9. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
29 more
  1. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  2. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  3. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
  4. 2018Generating Natural Language Adversarial Examplescited by 424
  5. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  6. 2013One Billion Word Benchmark for Measuring Progress in Statistical Language Modelingcited by 308
  7. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 286
  8. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  9. 2017Detecting Adversarial Samples from Artifactscited by 245
  10. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 207
  11. 2019Certified Robustness to Adversarial Word Substitutionscited by 168
  12. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 163
  13. 2017The Space of Transferable Adversarial Examplescited by 158
  14. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  15. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 140
  16. 2020Contextualized Perturbation for Textual Adversarial Attackcited by 136
  17. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 124
  18. 2020FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debuggingcited by 120
  19. 2021Towards Improving Adversarial Training of NLP Modelscited by 79
  20. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  21. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  22. 2020Robust Encodings: A Framework for Combating Adversarial Typoscited by 58
  23. 2019Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classificationcited by 57
  24. 2020Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examplescited by 54
  25. 2019When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signaturescited by 40
  26. 2021Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrificecited by 30
  27. 2021Detecting Textual Adversarial Examples through Randomized Substitution and Votecited by 8
  28. 2016Learning Robust Representations of Textcited by 6
  29. 2022Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representationscited by 2

Built on by

Not cited yet.