# Adversarial Vulnerability Transcends Computational Paradigms: Feature Engineering Provides No Defense Against Neural Adversarial Transfer

arXiv: https://arxiv.org/abs/2601.21323 · HTML: https://mlsanity.com/paper/2601.21323/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [On the Robustness of Vision Transformers to Adversarial Examples](https://mlsanity.com/paper/2104.02610/) (2021)
- [Backpropagating Linearly Improves Transferability of Adversarial Examples](https://mlsanity.com/paper/2012.03528/) (2020)
- [PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning](https://mlsanity.com/paper/2004.05682/) (2020)
- [Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently](https://mlsanity.com/paper/2112.14337/) (2021)
- [Learning Universal Adversarial Perturbations with Generative Models](https://mlsanity.com/paper/1708.05207/) (2017)
- [Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing](https://mlsanity.com/paper/2405.06340/) (2024)

## Abstract (arXiv)

Deep neural networks are vulnerable to adversarial examples--inputs with imperceptible perturbations causing misclassification. While adversarial transfer within neural networks is well-documented, whether classical ML pipelines using handcrafted features inherit this vulnerability when attacked via neural surrogates remains unexplored. Feature engineering creates information bottlenecks through gradient quantization and spatial binning, potentially filtering high-frequency adversarial signals. We evaluate this hypothesis through the first comprehensive study of adversarial transfer from DNNs to HOG-based classifiers. Using VGG16 as a surrogate, we generate FGSM and PGD adversarial examples and test transfer to four classical classifiers (KNN, Decision Tree, Linear SVM, Kernel SVM) and a shallow neural network across eight HOG configurations on CIFAR-10. Our results strongly refute the protective hypothesis: all classifiers suffer 16.6%-59.1% relative accuracy drops, comparable to neural-to-neural transfer. More surprisingly, we discover attack hierarchy reversal--contrary to patterns where iterative PGD dominates FGSM within neural networks, FGSM causes greater degradation than PGD in 100% of classical ML cases, suggesting iterative attacks overfit to surrogate-specific features that don't survive feature extraction. Block normalization provides partial but insufficient mitigation. These findings demonstrate that adversarial vulnerability is not an artifact of end-to-end differentiability but a fundamental property of image classification systems, with implications for security-critical deployments across computational paradigms.