Machine learning adoption has exploded over the past decade, driven in part by cloud computing. As vendors integrate machine learning into products across industries, security experts warn of adversarial attacks designed to abuse the technology. Data poisoning or model poisoning attacks involve polluting a machine learning model’s training data. The main problem with data poisoning is that it’s not easy to fix, depending on how the data is collected at certain intervals, depending upon the newly retrained with data collected with new models. The attacks can be used for a variety of purposes including disinformation and phishing scams.”]