mlsanityData to 7 Oct 2026

Distributed Black-box Attack: Do Not Overestimate Black-box Attacks

arXiv 2210.16371 ↗First posted 28 Oct 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

As cloud computing becomes pervasive, deep learning models are deployed on cloud servers and then provided as APIs to end users. However, black-box adversarial attacks can fool image classification models without access to model structure and weights. Recent studies have reported attack success rates of over 95% with fewer than 1,000 queries. Then the question arises: whether black-box attacks have become a real threat against cloud APIs? To shed some light on this, our research indicates that black-box attacks are not as effective against cloud APIs as proposed in research papers due to several common mistakes that overestimate the efficiency of black-box attacks. To avoid similar mistakes, we conduct black-box attacks directly on cloud APIs rather than local models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

21 of 27 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  10. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  11. 2017Countering Adversarial Images using Input Transformationscited by 517
  12. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
9 more
  1. 2020Meta Pseudo Labelscited by 372
  2. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  3. 2019Simple Black-box Adversarial Attackscited by 249
  4. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  5. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  6. 2019Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimizationcited by 49
  7. 2018Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attackscited by 46
  8. 2019A Survey of Black-Box Adversarial Attacks on Computer Vision Modelscited by 36
  9. 2019Exponentiated Gradient Meets Gradient Descentcited by 32

Built on by

Not cited yet.