mlsanityData to 7 Oct 2026

Integer-arithmetic-only Certified Robustness for Quantized Neural Networks

arXiv 2108.09413 ↗First posted 21 Aug 2021cs.LG cs.CR cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Adversarial data examples have drawn significant attention from the machine learning and security communities. A line of work on tackling adversarial examples is certified robustness via randomized smoothing that can provide a theoretical robustness guarantee. However, such a mechanism usually uses floating-point arithmetic for calculations in inference and requires large memory footprints and daunting computational costs. These defensive models cannot run efficiently on edge devices nor be deployed on integer-only logical units such as Turing Tensor Cores or integer-only ARM processors. To overcome these challenges, we propose an integer randomized smoothing approach with quantization to convert any classifier into a new smoothed classifier, which uses integer-only arithmetic for certified robustness against adversarial perturbations. We prove a tight robustness guarantee under L2-norm for the proposed approach. We show our approach can obtain a comparable accuracy and 4x~5x speedup over floating-point arithmetic certified robust methods on general-purpose CPUs and mobile devices on two distinct datasets (CIFAR-10 and Caltech-101).

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 37 of its 54 references that are in the map. First posted on arXiv 21 Aug 2021.

Builds on

37 of 54 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
25 more
  1. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  2. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  3. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  4. 2015Deep Learning with Limited Numerical Precisioncited by 368
  5. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  6. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  7. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  8. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  9. 2020The Discrete Gaussian for Differential Privacycited by 134
  10. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 122
  11. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  12. 2020APQ: Joint Search for Network Architecture, Pruning and Quantization Policycited by 98
  13. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
  14. 2019Model Compression with Adversarial Robustness: A Unified Optimization Frameworkcited by 71
  15. 2019Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifierscited by 65
  16. 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
  17. 2018Mixed Precision Training of Convolutional Neural Networks using Integer Operationscited by 45
  18. 2018On the Robustness of the CVPR 2018 White-Box Adversarial Example Defensescited by 40
  19. 2018Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networkscited by 38
  20. 2018Robust Adversarial Perturbation on Deep Proposal-based Modelscited by 26
  21. 2017Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Studycited by 25
  22. 2019Towards Compact and Robust Deep Neural Networkscited by 23
  23. 2017Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networkscited by 21
  24. 2018Unsupervised Learning using Pretrained CNN and Associative Memory Bankcited by 12
  25. 2019AddNet: Deep Neural Networks Using FPGA-Optimized Multiplierscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 0; 2026: 1.

7 papers.

  1. 2023Incremental Randomized Smoothing Certificationcited by 12
  2. 2024Investigating the Impact of Quantization on Adversarial Robustnesscited by 9
  3. 2023Learning Dynamic Graphs from All Contextual Information for Accurate Point-of-Interest Visit Forecastingcited by 6
  4. 2022Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networkscited by 3
  5. 2022Sound Randomized Smoothing in Floating-Point Arithmeticscited by 2
  6. 2024ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNscited by 1
  7. 2026T3C: Test-Time Tensor Compression with Consistency Guaranteescited by 0