mlsanityData to 14 Oct 2026

Security and Safety Aspects of AI in Industry Applications

arXiv 2207.10809 ↗First posted 16 Jul 2022cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this relatively informal discussion-paper we summarise issues in the domains of safety and security in machine learning that will affect industry sectors in the next five to ten years. Various products using neural network classification, most often in vision related applications but also in predictive maintenance, have been researched and applied in real-world applications in recent years. Nevertheless, reports of underlying problems in both safety and security related domains, for instance adversarial attacks have unsettled early adopters and are threatening to hinder wider scale adoption of this technology. The problem for real-world applicability lies in being able to assess the risk of applying these technologies. In this discussion-paper we describe the process of arriving at a machine-learnt neural network classifier pointing out safety and security vulnerabilities in that workflow, citing relevant research where appropriate.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 33 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

13 of 33 references.

References · 13

  1. 2013Intriguing properties of neural networkscited by 5,155
  2. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  3. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  4. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  5. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 180
  6. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  7. 2019Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classificationcited by 55
  8. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  9. 2021RTGPU: Real-Time GPU Scheduling of Hard Deadline Parallel Tasks with Fine-Grain Utilizationcited by 3
  10. 2018A Survey of Techniques for Improving Security of GPUscited by 2
  11. 2021Dynamic Lockstep Processors for Applications with Functional Safety Relevancecited by 2
  12. 2020Designing Neural Networks for Real-Time Systemscited by 1
1 more
  1. 2021Dependable Neural Networks Through Redundancy, A Comparison of Redundant Architecturescited by 1

Built on by

Not cited yet.