mlsanityData to 14 Oct 2026

Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers

arXiv 2404.11665 ↗First posted 17 Apr 2024cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have advanced in many real-world applications, such as healthcare and autonomous driving. However, their high computational complexity and vulnerability to adversarial attacks are ongoing challenges. In this letter, approximate multipliers are used to explore DNN robustness improvement against adversarial attacks. By uniformly replacing accurate multipliers for state-of-the-art approximate ones in DNN layer models, we explore the DNNs robustness against various adversarial attacks in a feasible time. Results show up to 7% accuracy drop due to approximations when no attack is present while improving robust accuracy up to 10% when attacks applied.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

10 of 29 references.

References · 10

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial Machine Learning at Scalecited by 936
  7. 2022Hardware Approximate Techniques for Deep Neural Network Accelerators: A Surveycited by 39
  8. 2020EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attackscited by 28
  9. 2022AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorchcited by 11
  10. 2023scaleTRIM: Scalable TRuncation-Based Integer Approximate Multiplier with Linearization and Compensationcited by 3

Built on by

Not cited yet.