Targeted Attacks on Timeseries Forecasting. (arXiv:2301.11544v1 [cs.LG])

Real-world deep learning models developed for Time Series Forecasting are
used in several critical applications ranging from medical devices to the
security domain. Many previous works have shown how deep learning models are
prone to adversarial attacks and studied their vulnerabilities. However, the
vulnerabilities of time series models for forecasting due to adversarial inputs
are not extensively explored. While the attack on a forecasting model might aim
to deteriorate the performance of the model, it is more effective, if the …

adversarial adversarial attacks aim applications attack attacks critical deep learning devices domain forecasting inputs medical medical devices performance security series targeted attacks vulnerabilities world