Doorgaan naar hoofdnavigatie Doorgaan naar zoeken Ga verder naar hoofdinhoud

Risks of uncertainty propagation in Al-augmented security pipelines

  • Emanuele Mezzi
  • , Aurora Papotti
  • , Fabio Massacci
  • , Katja Tuma

Onderzoeksoutput: WerkdocumentPreprintAcademic

Samenvatting

The use of AI technologies is percolating into the secure development of software-based systems, with an increasing trend of composing AI-based subsystems (with uncertain levels of performance) into automated pipelines. This presents a fundamental research challenge and poses a serious threat to safety-critical domains (e.g., aviation). Despite the existing knowledge about uncertainty in risk analysis, no previous work has estimated the uncertainty of AI-augmented systems given the propagation of errors in the pipeline. We provide the formal underpinnings for capturing uncertainty propagation, develop a simulator to quantify uncertainty, and evaluate the simulation of propagating errors with two case studies. We discuss the generalizability of our approach and present policy implications and recommendations for aviation. Future work includes extending the approach and investigating the required metrics for validation in the aviation domain.
Originele taal-2Engels
UitgeverarXiv.org
Volume2407.14540
DOI's
StatusGepubliceerd - 14 jul. 2024
Extern gepubliceerdJa

Trefwoorden

  • cs.SE
  • cs.AI
  • cs.CR

Vingerafdruk

Duik in de onderzoeksthema's van 'Risks of uncertainty propagation in Al-augmented security pipelines'. Samen vormen ze een unieke vingerafdruk.

Citeer dit