Webinar: Securing ML Models in Production

About the Webinar: 

Machine Learning models are popping up everywhere around us, be it e-commerce, food delivery, taxis, networks or healthcare. We went through a journey of running these models on a local system to industrializing these models and scaling them to serve millions of users using cutting edge cloud technologies. However, very few people actually realize how easy / hard these models are to hack & replicate using various black box & white box methodologies.

This talk will walk you through important security aspects one has to keep in mind while deploying machine learning models on cloud, edge or on-premise. We will also showcase counter measures to defend these attacks as well.

Key Takeaways from the Webinar:

We will take the standard security expert's approach of:

1. Awareness
2. Applicability
3. Countermeasures

The talk will majorly focus attacks like:

1. Model extraction - How can an adversary replicate your model?
2. Model evasion / adversarial attacks - How can an adversary corrupt your model? 3. Model watermarking - How can one prove ownership of a model

 

Who is this Webinar for?

Data Scientists, Machine Learning Engineers, Architects, CTOs deploying ML models in production & scaling them on cloud.

Speakers: 

Raghotham Sripadraj, Senior Data Scientist - Ericsson GAIA

Raghotham Sripadraj is Senior Data Scientist at Ericsson GAIA. Previously, he co founded Unnati Data Labs, where he was responsible for building end-to-end data science systems in the fields of fintech, marketing analytics, and event management. He led the ML team at Treebo hotels. Drawing on his deep love for data science and neural networks and his passion for teaching, Raghotham has conducted workshops and is a frequent speaker at various data science conferences.

Rajib Biswas, Lead Data Scientist - Ericsson GAIA

Rajib Biswas([email protected]) is a Lead Data Scientist working at Global Artificial Intelligence Accelerator (GAIA) at Ericsson, Bangalore. He pursued M.Engg in Computer Science from BITS-Pilani. Over his professional career of 13 years, he has worked on AI research and product development with organizations like Intel, Samsung, Fidelity Investments . He has worked on Natural language processing, Computer vision and Deep learning to solve business problems in finance and telecom domain. Couple of his patent applications are pending in US PTO and he has presented his research work in different international conferences/forums.