mlsanityData to 7 Oct 2026

Black-box adversarial attacks using Evolution Strategies

arXiv 2104.15064 ↗First posted 30 Apr 2021cs.CV cs.LG cs.NEcited by 11

Not on the map. Why?

Abstract (arXiv)

In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to perturbations of the input data. In fact, several studies showed that slightly changing the content of the images can cause a dramatic decrease in the accuracy of the attacked neural network. Several methods able to generate adversarial samples make use of gradients, which usually are not available to an attacker in real-world scenarios. As opposed to this class of attacks, another class of adversarial attacks, called black-box adversarial attacks, emerged, which does not make use of information on the gradients, being more suitable for real-world attack scenarios. In this work, we compare three well-known evolution strategies on the generation of black-box adversarial attacks for image classification tasks. While our results show that the attacked neural networks can be, in most cases, easily fooled by all the algorithms under comparison, they also show that some black-box optimization algorithms may be better in "harder" setups, both in terms of attack success rate and efficiency (i.e., number of queries).

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

25 of 37 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  10. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  11. 2017One pixel attack for fooling deep neural networkscited by 579
  12. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
13 more
  1. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  2. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  3. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  4. 2019Simple Black-box Adversarial Attackscited by 249
  5. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 148
  6. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  7. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  8. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 60
  9. 2021A Survey On Universal Adversarial Attackcited by 59
  10. 2016Simple Black-Box Adversarial Perturbations for Deep Networkscited by 42
  11. 2019A Survey of Black-Box Adversarial Attacks on Computer Vision Modelscited by 36
  12. 2019POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithmcited by 14
  13. 2019Online Selection of CMA-ES Variantscited by 11

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 7; 2025: 2.

11 papers.

  1. 2022Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Modelscited by 13
  2. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  3. 2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
  4. 2024Machine Learning Robustness: A Primercited by 8
  5. 2024On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoningcited by 4
  6. 2024Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systemscited by 2
  7. 2025Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategiescited by 1
  8. 2024EGAN: Evolutional GAN for Ransomware Evasioncited by 0
  9. 2024Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instancescited by 0
  10. 2024Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysiscited by 0
  11. 2025EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanationscited by 0