mlsanityData to 14 Oct 2026

Robustness Analysis of Deep Learning Frameworks on Mobile Platforms

arXiv 2109.09869 ↗First posted 20 Sep 2021cs.LG cs.SEcited by 1

Not on the map. Why?

Abstract (arXiv)

With the recent increase in the computational power of modern mobile devices, machine learning-based heavy tasks such as face detection and speech recognition are now integral parts of such devices. This requires frameworks to execute machine learning models (e.g., Deep Neural Networks) on mobile devices. Although there exist studies on the accuracy and performance of these frameworks, the quality of on-device deep learning frameworks, in terms of their robustness, has not been systematically studied yet. In this paper, we empirically compare two on-device deep learning frameworks with three adversarial attacks on three different model architectures. We also use both the quantized and unquantized variants for each architecture. The results show that, in general, neither of the deep learning frameworks is better than the other in terms of robustness, and there is not a significant difference between the PC and mobile frameworks either. However, in cases like Boundary attack, mobile version is more robust than PC. In addition, quantization improves robustness in all cases when moving from PC to mobile.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 20 Sep 2021.

Builds on

18 of 31 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2016Adversarial examples in the physical worldcited by 1,769
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  10. 2017One pixel attack for fooling deep neural networkscited by 582
  11. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  12. 2015MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systemscited by 195
6 more
  1. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
  2. 2016Robustness of classifiers: from adversarial to random noisecited by 88
  3. 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
  4. 2019An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platformscited by 35
  5. 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
  6. 2020Comparison and Benchmarking of AI Models and Frameworks on Mobile Devicescited by 17

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Mobile Foundation Model as Firmwarecited by 25

Similar, not cited

Close in wording, no citation either way

  1. 2023RobustMQ: Benchmarking Robustness of Quantized Models
  2. 2023Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks
  3. 2023Benchmarking the Robustness of Quantized Models
  4. 2024Investigating the Impact of Quantization on Adversarial Robustness
  5. 2022Adaptation of MobileNetV2 for Face Detection on Ultra-Low Power Platform
  6. 2025Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks
  7. 2022Benchmarking of DL Libraries and Models on Mobile Devices
  8. 2021On the Adversarial Robustness of Quantized Neural Networks