Adversarial Attack’s Impact on Machine Learning Model in Cyber-Physical Systems

Abstract

Deficiency of correctly implemented and robust defence leaves Internet of Things devices vulnerable to cyber threats, such as adversarial attacks. A perpetrator can utilize adversarial examples when attacking Machine Learning models used in a cloud data platform service. Adversarial examples are malicious inputs to ML-models that provide erroneous model outputs while appearing to be unmodified. This kind of attack can fool the classifier and can prevent ML-models from generalizing well and from learning high-level representation; instead, the ML-model learns superficial dataset regularity. This study focuses on investigating, detecting, and preventing adversarial attacks towards a cloud data platform in the cyber-physical context.