# Generating Black-Box Adversarial Examples in Sparse Domain

arXiv: https://arxiv.org/abs/2101.09324 · HTML: https://mlsanity.com/paper/2101.09324/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 22 Jan 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Technical Report on the CleverHans v2.1.0 Adversarial Examples Library](https://mlsanity.com/paper/1610.00768/) (2016)
- [Towards the Science of Security and Privacy in Machine Learning](https://mlsanity.com/paper/1611.03814/) (2016)
- [Low Frequency Adversarial Perturbation](https://mlsanity.com/paper/1809.08758/) (2018)
- [Adversarial Attacks Beyond the Image Space](https://mlsanity.com/paper/1711.07183/) (2017)
- [On the Effectiveness of Low Frequency Perturbations](https://mlsanity.com/paper/1903.00073/) (2019)
- [Security Evaluation of Pattern Classifiers under Attack](https://mlsanity.com/paper/1709.00609/) (2017)
- [Blocking Transferability of Adversarial Examples in Black-Box Learning Systems](https://mlsanity.com/paper/1703.04318/) (2017)

## Built on by (most cited first, 2 of 2)

- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume](https://mlsanity.com/paper/2403.05100/) (2024)

## Abstract (arXiv)

Applications of machine learning (ML) models and convolutional neural networks (CNNs) have been rapidly increased. Although state-of-the-art CNNs provide high accuracy in many applications, recent investigations show that such networks are highly vulnerable to adversarial attacks. The black-box adversarial attack is one type of attack that the attacker does not have any knowledge about the model or the training dataset, but it has some input data set and their labels. In this paper, we propose a novel approach to generate a black-box attack in sparse domain whereas the most important information of an image can be observed. Our investigation shows that large sparse (LaS) components play a critical role in the performance of image classifiers. Under this presumption, to generate adversarial example, we transfer an image into a sparse domain and put a threshold to choose only k LaS components. In contrast to the very recent works that randomly perturb k low frequency (LoF) components, we perturb k LaS components either randomly (query-based) or in the direction of the most correlated sparse signal from a different class. We show that LaS components contain some middle or higher frequency components information which leads fooling image classifiers with a fewer number of queries. We demonstrate the effectiveness of this approach by fooling six state-of-the-art image classifiers, the TensorFlow Lite (TFLite) model of Google Cloud Vision platform, and YOLOv5 model as an object detection algorithm. Mean squared error (MSE) and peak signal to noise ratio (PSNR) are used as quality metrics. We also present a theoretical proof to connect these metrics to the level of perturbation in the sparse domain.