We can easily trick a classifier into making embarrassingly false predictions. When this is done systematically and intentionally, it is called an adversarial attack. Specifically, this kind of attack is called an evasion attack. In this session, we will examine an evasion use case and briefly explain other forms of attacks. Then, we explain two defense methods: spatial smoothing preprocessing and adversarial training. Lastly, we will demonstrate one robustness evaluation method and one certification method to ascertain that the model can withstand such attacks.
PRO WORKSHOP: Making Machine Learning Models Attack-Proof with Adversarial Robustness
Serg Masís has been at the confluence of the internet, application development, and analytics for the last two decades. Currently, he's a Climate and Agronomic Data Scientist at Syngenta, a leading agribusiness company with a mission to improve global food security. Before that role, he co-founded a search engine startup, incubated by Harvard Innovation Labs, that combined the power of cloud computing and machine learning with principles in decision-making science to expose users to new places and events efficiently. Whether it pertains to leisure activities, plant diseases, or customer lifetime value, Serg is passionate about providing the often-missing link between data and decision-making — and machine learning interpretation helps bridge this gap more robustly. His book titled "Interpretable Machine Learning with Python" is scheduled to be released in early 2021 by UK-based publisher Packt