# WaveTransform: Crafting Adversarial Examples via Input Decomposition

arXiv: https://arxiv.org/abs/2010.15773 · HTML: https://mlsanity.com/paper/2010.15773/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization](https://mlsanity.com/paper/2102.10707/) (2021)
- [Wavelet Regularization Benefits Adversarial Training](https://mlsanity.com/paper/2206.03727/) (2022)
- [DFT-Based Adversarial Attack Detection in MRI Brain Imaging: Enhancing Diagnostic Accuracy in Alzheimer's Case Studies](https://mlsanity.com/paper/2408.08489/) (2024)
- [SegWave: Wavelet-Driven Segmentation of Tampered Regions](https://mlsanity.com/paper/2608.30714/) (2026)

## Abstract (arXiv)

Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation learning techniques, including deep learning. Inspired by this observation, we introduce a novel class of adversarial attacks, namely `WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination). The frequency subbands are analyzed using wavelet decomposition; the subbands are corrupted and then used to construct an adversarial example. Experiments are performed using multiple databases and CNN models to establish the effectiveness of the proposed WaveTransform attack and analyze the importance of a particular frequency component. The robustness of the proposed attack is also evaluated through its transferability and resiliency against a recent adversarial defense algorithm. Experiments show that the proposed attack is effective against the defense algorithm and is also transferable across CNNs.