mlsanityData to 14 Oct 2026

Effective Universal Unrestricted Adversarial Attacks using a MOE Approach

arXiv 2103.00250 ↗First posted 27 Feb 2021cs.LG cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested evolutionary algorithm to generate universal unrestricted adversarial examples in a black-box scenario. The unrestricted attacks are performed through the application of well-known image filters that are available in several image processing libraries, modern cameras, and mobile applications. The multi-objective optimization takes into account not only the attack success rate but also the detection rate. Experimental results showed that this approach is able to create a sequence of filters capable of generating very effective and undetectable attacks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 27 Feb 2021.

Builds on

28 of 41 references.

References · 28

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  6. 2016Adversarial Machine Learning at Scalecited by 936
  7. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  8. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  9. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  10. 2016Universal adversarial perturbationscited by 784
  11. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  12. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
16 more
  1. 2017One pixel attack for fooling deep neural networkscited by 582
  2. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  3. 2017NIMA: Neural Image Assessmentcited by 389
  4. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  5. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  6. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  7. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  8. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  9. 2018Semantic Adversarial Examplescited by 86
  10. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  11. 2017Defense against Universal Adversarial Perturbationscited by 48
  12. 2018Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressionscited by 31
  13. 2019Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructionscited by 30
  14. 2019EdgeFool: An Adversarial Image Enhancement Filtercited by 10
  15. 2019Adversarial Example Generation using Evolutionary Multi-objective Optimizationcited by 9
  16. 2019They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimizationcited by 4

Built on by

Cited by year

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

4 papers.

  1. 2021Effective and Imperceptible Adversarial Textual Attack via Multi-objectivizationcited by 5
  2. 2024Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolumecited by 3
  3. 2023Black-box Attacks on Image Activity Prediction and its Natural Language Explanationscited by 1
  4. 2025MOS-Attack: A Scalable Multi-objective Adversarial Attack Frameworkcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Content-based Unrestricted Adversarial Attack
  2. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
  3. 2025Gradient-Free Adversarial Purification with Diffusion Models
  4. 2024Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!
  5. 2024Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
  6. 2025VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models
  7. 2026Fast Adversarial Attacks with Gradient Prediction
  8. 2023Assessing Robustness via Score-Based Adversarial Image Generation