mlsanityData to 14 Oct 2026

Explaining high-dimensional text classifiers

arXiv 2311.13454 ↗First posted 22 Nov 2023cs.LG cs.CR cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Explainability has become a valuable tool in the last few years, helping humans better understand AI-guided decisions. However, the classic explainability tools are sometimes quite limited when considering high-dimensional inputs and neural network classifiers. We present a new explainability method using theoretically proven high-dimensional properties in neural network classifiers. We present two usages of it: 1) On the classical sentiment analysis task for the IMDB reviews dataset, and 2) our Malware-Detection task for our PowerShell scripts dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 22 Nov 2023.

Builds on

20 of 28 references.

References · 20

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  7. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  8. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  10. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
  11. 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
  12. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
8 more
  1. 2018Pathologies of Neural Models Make Interpretations Difficultcited by 140
  2. 2020You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completioncited by 131
  3. 2020Shapley explainability on the data manifoldcited by 88
  4. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 72
  5. 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
  6. 2018Towards Explainable NLP: A Generative Explanation Framework for Text Classificationcited by 55
  7. 2021The Dimpled Manifold Model of Adversarial Examples in Machine Learningcited by 41
  8. 2018Interpreting Neural Networks With Nearest Neighborscited by 18

Built on by

Not cited yet.