Anomaly detection is a continuing pressing concern for data scientists in this coming age. Being able to detect fraudulent bank transfers, insurance claims, or even messages and transmissions through a cyber-physical system are becoming of increasing importance to maintain the health and well being of people in society, as well as protecting their data and assets. With the growing connection between manufacturing, energy services, transport systems and aerial systems with an online system for storage or modelling allows for the infiltration of attacks to such information. Allowing for fabrication of information within the system, which can create disastrous circumstances. Examples of such threats are the Stuxnet worm that targeted a nuclear power plant, Ukraine power outages, auto-driving crashes and robot malfunctions as well as a threat to the Australian MoochyWater service.
Development of statistical methodologies to perform anomaly detection on a dataset
2022
Abstract
Anomaly detection is a continuing pressing concern for data scientists in this coming age. Being able to detect fraudulent bank transfers, insurance claims, or even messages and transmissions through a cyber-physical system are becoming of increasing importance to maintain the health and well being of people in society, as well as protecting their data and assets. With the growing connection between manufacturing, energy services, transport systems and aerial systems with an online system for storage or modelling allows for the infiltration of attacks to such information. Allowing for fabrication of information within the system, which can create disastrous circumstances. Examples of such threats are the Stuxnet worm that targeted a nuclear power plant, Ukraine power outages, auto-driving crashes and robot malfunctions as well as a threat to the Australian MoochyWater service.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.