mlsanityData to 14 Oct 2026

On the Computational Entanglement of Distant Features in Adversarial Machine Learning

arXiv 2309.15669 ↗First posted 27 Sep 2023cs.LG cs.IT math.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

In this research, we introduce the concept of "computational entanglement," a phenomenon observed in overparameterized feedforward linear networks that enables the network to achieve zero loss by fitting random noise, even on previously unseen test samples. Analyzing this behavior through spacetime diagrams reveals its connection to length contraction, where both training and test samples converge toward a shared normalized point within a flat Riemannian manifold. Moreover, we present a novel application of computational entanglement in transforming a worst-case adversarial examples-inputs that are highly non-robust and uninterpretable to human observers-into outputs that are both recognizable and robust. This provides new insights into the behavior of non-robust features in adversarial example generation, underscoring the critical role of computational entanglement in enhancing model robustness and advancing our understanding of neural networks in adversarial contexts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 81 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

29 of 81 references.

References · 29

  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. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  5. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  6. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
  7. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
  8. 2019Implicit Regularization in Deep Matrix Factorizationcited by 405
  9. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 334
  10. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  11. 2018Spatially Transformed Adversarial Examplescited by 195
  12. 2018Robustness via curvature regularization, and vice versacited by 175
17 more
  1. 2018Disentangling Adversarial Robustness and Generalizationcited by 172
  2. 2019An Improved Analysis of Training Over-parameterized Deep Neural Networkscited by 121
  3. 2018Are adversarial examples inevitable?cited by 113
  4. 2018Adversarial examples from computational constraintscited by 80
  5. 2018Adversarial Examples that Fool both Computer Vision and Time-Limited Humanscited by 73
  6. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  7. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 62
  8. 2020Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rankcited by 42
  9. 2018Understanding and Enhancing the Transferability of Adversarial Examplescited by 41
  10. 2021The Dimpled Manifold Model of Adversarial Examples in Machine Learningcited by 41
  11. 2018Unrestricted Adversarial Examplescited by 40
  12. 2020Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspectivecited by 35
  13. 2019A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distancecited by 32
  14. 2021Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differentlycited by 22
  15. 2021ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networkscited by 8
  16. 2021Disrupting Model Training with Adversarial Shortcutscited by 7
  17. 2022Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networkscited by 1

Built on by

Not cited yet.