# On the Computational Entanglement of Distant Features in Adversarial Machine Learning

arXiv: https://arxiv.org/abs/2309.15669 · HTML: https://mlsanity.com/paper/2309.15669/

## 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 (most cited first, 29 of 29)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Implicit Regularization in Deep Matrix Factorization](https://mlsanity.com/paper/1905.13655/) (2019)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Spatially Transformed Adversarial Examples](https://mlsanity.com/paper/1801.02612/) (2018)
- [Robustness via curvature regularization, and vice versa](https://mlsanity.com/paper/1811.09716/) (2018)
- [Disentangling Adversarial Robustness and Generalization](https://mlsanity.com/paper/1812.00740/) (2018)
- [An Improved Analysis of Training Over-parameterized Deep Neural Networks](https://mlsanity.com/paper/1906.04688/) (2019)
- [Are adversarial examples inevitable?](https://mlsanity.com/paper/1809.02104/) (2018)
- [Adversarial examples from computational constraints](https://mlsanity.com/paper/1805.10204/) (2018)
- [Adversarial Examples that Fool both Computer Vision and Time-Limited Humans](https://mlsanity.com/paper/1802.08195/) (2018)
- [A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples](https://mlsanity.com/paper/1608.07690/) (2016)
- [Adversarial Transformation Networks: Learning to Generate Adversarial Examples](https://mlsanity.com/paper/1703.09387/) (2017)
- [Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank](https://mlsanity.com/paper/2011.13772/) (2020)
- [The Dimpled Manifold Model of Adversarial Examples in Machine Learning](https://mlsanity.com/paper/2106.10151/) (2021)
- [Understanding and Enhancing the Transferability of Adversarial Examples](https://mlsanity.com/paper/1802.09707/) (2018)
- [Unrestricted Adversarial Examples](https://mlsanity.com/paper/1809.08352/) (2018)
- [Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective](https://mlsanity.com/paper/2010.03316/) (2020)
- [A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance](https://mlsanity.com/paper/1901.10861/) (2019)
- [Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently](https://mlsanity.com/paper/2112.14337/) (2021)
- [ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2107.07677/) (2021)
- [Disrupting Model Training with Adversarial Shortcuts](https://mlsanity.com/paper/2106.06654/) (2021)
- [Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks](https://mlsanity.com/paper/2206.04316/) (2022)

## 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.