Although machine learning is widely used in practice, little is known about practitioners' understanding of potential security challenges. In this work, we close this substantial gap and contribute a qualitative study focusing on developers' mental models of the machine learning pipeline and potentially vulnerable components. Similar studies have helped in other security fields to discover root causes or improve risk communication. Our study reveals two facets of practitioners' mental models of machine learning security. Firstly, practitioners often confuse machine learning security with threats and defences that are not directly related to machine learning. Secondly, in contrast to most academic research, our participants perceive security of machine learning as not solely related to individual models, but rather in the context of entire workflows that consist of multiple components. Jointly with our additional findings, these two facets provide a foundation to substantiate mental models for machine learning security and have implications for the integration of adversarial machine learning into corporate workflows, decreasing practitioners' reported uncertainty, and appropriate regulatory frameworks for machine learning security.
Industrial practitioners' mental models of adversarial machine learning
Grosse K.;Biggio B.;
2022-01-01
Abstract
Although machine learning is widely used in practice, little is known about practitioners' understanding of potential security challenges. In this work, we close this substantial gap and contribute a qualitative study focusing on developers' mental models of the machine learning pipeline and potentially vulnerable components. Similar studies have helped in other security fields to discover root causes or improve risk communication. Our study reveals two facets of practitioners' mental models of machine learning security. Firstly, practitioners often confuse machine learning security with threats and defences that are not directly related to machine learning. Secondly, in contrast to most academic research, our participants perceive security of machine learning as not solely related to individual models, but rather in the context of entire workflows that consist of multiple components. Jointly with our additional findings, these two facets provide a foundation to substantiate mental models for machine learning security and have implications for the integration of adversarial machine learning into corporate workflows, decreasing practitioners' reported uncertainty, and appropriate regulatory frameworks for machine learning security.File | Dimensione | Formato | |
---|---|---|---|
soups2022-bieringer.pdf
accesso aperto
Tipologia:
versione editoriale (VoR)
Dimensione
1.29 MB
Formato
Adobe PDF
|
1.29 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.