mlsanityData to 7 Oct 2026

Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems

arXiv 2104.08690 ↗First posted 18 Apr 2021cs.LG cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm. In this paper, we investigate the interplay between vulnerabilities of the image scaling procedure and machine learning models in the decision-based black-box setting. We propose a novel sampling strategy to make a black-box attack exploit vulnerabilities in scaling algorithms, scaling defenses, and the final machine learning model in an end-to-end manner. Based on this scaling-aware attack, we reveal that most existing scaling defenses are ineffective under threat from downstream models. Moreover, we empirically observe that standard black-box attacks can significantly improve their performance by exploiting the vulnerable scaling procedure. We further demonstrate this problem on a commercial Image Analysis API with decision-based black-box attacks.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 18 Apr 2021.

Builds on

41 of 55 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  11. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  12. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
29 more
  1. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  2. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  3. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  4. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  5. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  6. 2017Countering Adversarial Images using Input Transformationscited by 517
  7. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  8. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  10. 2019On Evaluating Adversarial Robustnesscited by 442
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2019Simple Black-box Adversarial Attackscited by 249
  13. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  14. 2016A guide to convolution arithmetic for deep learningcited by 182
  15. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  16. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  17. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  18. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  19. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
  20. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
  21. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  22. 2020Evading Deepfake-Image Detectors with White- and Black-Box Attackscited by 80
  23. 2020GeoDA: a geometric framework for black-box adversarial attackscited by 66
  24. 2020Backdooring and Poisoning Neural Networks with Image-Scaling Attackscited by 28
  25. 2020Face-Off: Adversarial Face Obfuscationcited by 25
  26. 2020Projection & Probability-Driven Black-Box Attackcited by 19
  27. 2020FoggySight: A Scheme for Facial Lookup Privacycited by 12
  28. 2020Security and Machine Learning in the Real Worldcited by 9
  29. 2021Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attackscited by 9

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 2; 2024: 1.

7 papers.

  1. 2022Architectural Backdoors in Neural Networkscited by 24
  2. 2022On the Limitations of Stochastic Pre-processing Defensescited by 21
  3. 2024Architectural Neural Backdoors from First Principlescited by 10
  4. 2022Augmentation Backdoorscited by 5
  5. 2022Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systemscited by 5
  6. 2023SEA: Shareable and Explainable Attribution for Query-based Black-box Attackscited by 0
  7. 2023On the Detection of Image-Scaling Attacks in Machine Learningcited by 0