Adversarial Attacks on Time Series Data

Security vulnerabilities of state-of-art deep learning model for time series (LSTM) are exposed for regression and classification by adversarial attacks: Basic Iterative and Fast Gradient Sign Method.

avatar Afra Akbaş
avatar Ceren Tahtasız
poster
Poster

Security vulnerabilities of state-of-art deep learning model for time series (LSTM) are exposed for regression and classification by adversarial attacks: Basic Iterative and Fast Gradient Sign Method.

Poster: https://drive.google.com/file/d/1bH2Z5Fhx5Q9NDFIUky97ATNkm23UWfHM/view?usp=sharing

Video: https://drive.google.com/file/d/1Sucs2WPe4UPsCpvR2e5rF0Bbs9HnauNH/view?usp=sharing

Advisors

İnci Meliha Baytaş