mlsanityData to 14 Oct 2026

Resilience of Deep Learning applications: a systematic literature review of analysis and hardening techniques

arXiv 2309.16733 ↗First posted 27 Sep 2023cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Machine Learning (ML) is currently being exploited in numerous applications being one of the most effective Artificial Intelligence (AI) technologies, used in diverse fields, such as vision, autonomous systems, and alike. The trend motivated a significant amount of contributions to the analysis and design of ML applications against faults affecting the underlying hardware. The authors investigate the existing body of knowledge on Deep Learning (among ML techniques) resilience against hardware faults systematically through a thoughtful review in which the strengths and weaknesses of this literature stream are presented clearly and then future avenues of research are set out. The review is based on 220 scientific articles published between January 2019 and March 2024. The authors adopt a classifying framework to interpret and highlight research similarities and peculiarities, based on several parameters, starting from the main scope of the work, the adopted fault and error models, to their reproducibility. This framework allows for a comparison of the different solutions and the identification of possible synergies. Furthermore, suggestions concerning the future direction of research are proposed in the form of open challenges to be addressed.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 15 of its 108 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

15 of 108 references.

References · 15

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 288
  3. 2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 150
  4. 2019FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activationcited by 31
  5. 2018Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Acceleratorcited by 25
  6. 2020FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networkscited by 21
  7. 2019When Single Event Upset Meets Deep Neural Networks: Observations, Explorations, and Remediescited by 15
  8. 2020FAT: Training Neural Networks for Reliable Inference Under Hardware Faultscited by 15
  9. 2020Making Convolutions Resilient via Algorithm-Based Error Detection Techniquescited by 12
  10. 2021FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functionscited by 12
  11. 2023DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Acceleratorscited by 11
  12. 2019In-Place Zero-Space Memory Protection for CNNcited by 9
3 more
  1. 2021Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUscited by 9
  2. 2022Fast and Accurate Error Simulation for CNNs against Soft Errorscited by 7
  3. 2023Exposing Reliability Degradation and Mitigation in Approximate DNNs under Permanent Faultscited by 4

Built on by

Cited by year (2026 to 14 Oct)

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

4 papers.

  1. 2024DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural Networkcited by 1
  2. 2025Efficient Triple Modular Redundancy for Reliability Enhancement of DNNs Using Explainable AIcited by 0
  3. 2026CoG-Guided Weight Correction for Fault-Tolerant Deep Neural Networkscited by 0
  4. 2026TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networkscited by 0