@article{fdi:010093428,
  title = {{S}afety monitoring of machine learning perception functions : a survey},
  author = {{F}erreira, {R}. {S}. and {G}uerin, {J}oris and {D}elmas, {K}. and {G}uiochet, {J}. and {W}aeselynck, {H}.},
  editor = {},
  language = {{ENG}},
  abstract = {{M}achine {L}earning ({ML}) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. {N}ew dependability challenges arise when {ML} predictions are used in safety-critical applications, like autonomous cars and surgical robots. {T}hus, the use of fault tolerance mechanisms, such as safety monitors, is essential to ensure the safe behavior of the system despite the occurrence of faults. {T}his paper presents an extensive literature review on safety monitoring of perception functions using {ML} in a safety-critical context. {I}n this review, we structure the existing literature to highlight key factors to consider when designing such monitors: threat identification, requirements elicitation, detection of failure, reaction, and evaluation. {W}e also highlight the ongoing challenges associated with safety monitoring and suggest directions for future research.},
  keywords = {fault tolerance ; machine learning perception ; runtime monitoring ; safety-critical autonomous systems},
  booktitle = {},
  journal = {{C}omputational {I}ntelligence},
  volume = {41},
  numero = {2},
  pages = {e70032 [20 p.]},
  ISSN = {0824-7935},
  year = {2025},
  DOI = {10.1111/coin.70032},
  URL = {https://www.documentation.ird.fr/hor/fdi:010093428},
}