This paper looks at how threat actors can manipulate and poison machine learning training, to twist the systems to their goals. The goals are achieved without impacting the integrity of the underlying data sets. Manipulating SGD with Data Ordering Attacks (arxiv.org) Shumailov, I., Shumaylov, Z., Kazhdan, D., Zhao, Y., Papernot, …
Continue reading “Machine learning is vulnerable to a wide variety of attacks”
