Securing Machine Learning Systems and Environments in the Cloud
FinOps – Think Data to Get Back Control Of Your Mainframe Costs
November 21, 2022
Ensuring the Mainframe is an Integral Part of Your Enterprise Observability Strategy
November 21, 2022
There are different ways to attack machine learning systems and most data science teams are not equipped with the skills to secure these systems. In this talk, we will talk about the different ways these systems can be attacked and then we will share relevant strategies to protect these systems.
Designing and building machine learning systems require a lot of skill, time, and experience. Data scientists, developers, and ML engineers work together in building ML systems and pipelines that automate different stages of the machine learning process. Once the ML systems have been set up, these systems need to be secured properly to prevent these systems from being hacked and compromised.
Some attacks have been customized to take advantage of vulnerabilities present in certain libraries. Other attacks may take advantage of vulnerabilities present in the custom code of ML engineers as well. There are different ways to attack machine learning systems and most data science teams are not equipped with the skills required to secure the systems they built. In this talk, we will discuss in detail the cybersecurity attack chain and how this affects a company’s strategy when setting up different layers of security. We will discuss the different ways ML systems can be attacked and compromised and along the way, we will share the relevant strategies to mitigate these attacks. Finally, we will talk about the different types of attacks on data privacy and ML model privacy which includes membership inference attack, model extraction attack, attribute inference
Presented by
Joshua Arvin Lat, Chief Technology Officer at NuWorks Interactive Labs, Inc.
Joshua Arvin Lat is the Chief Technology Officer (CTO) of NuWorks Interactive Labs, Inc. He previously served as the CTO of three Australian-owned companies and also served as the Director for Software Development and Engineering for multiple e-commerce start-ups in the past, which allowed him to be more effective as a leader. Years ago, he and his team won first place in a global cybersecurity competition with their published research paper. He is also an AWS Machine Learning Hero and has shared his knowledge at several international conferences, discussing practical strategies on machine learning, engineering, security, and management. He is the author of the books “Machine Learning with Amazon SageMaker Cookbook” and “Machine Learning Engineering on AWS”
– Conf42: JavaScript 2022 – Building Machine Learning-powered applications in JavaScript
– Data Science Summit 2022 – Machine Learning Model Deployment and Monitoring Strategies
– AWS Summit ASEAN 2022 – Building machine learning workflows using Amazon SageMaker Pipelines
– DevOps Summit – North America 2022 – Designing and Building CI/CD Pipelines in the Cloud: Serverless x Containers
– WARSAW IT DAYS 2022 – Pragmatic Machine Learning Engineering in the Cloud
– The DEVOPS Conference 2022 – Pragmatic Security Automation and DevSecOps in the Cloud
– DevSecOps Conf 2022 – Pragmatic Security Automation and DevSecOps in the Cloud
– PyCon APAC 2021 – Machine Learning Engineering Done Right: Designing and Building Complex Intelligent Systems and Workflows with Python
(and more)
Links to recorded videos:
– AWS Summit Singapore [Day 1: TechFest] – Pragmatic Serverless Strategies for Modern Applications – https://www.youtube.com/watch?v=d_abBFnNkNk
– Machine Learning Engineering Done Right Joshua Arvin Lat Conf42 Python 2021 — https://www.youtube.com/watch?v=KM00eyKDVs4
– Designing and Building Serverless Machine Learning-powered Applications with Python – Joshua Arvin Lat— https://www.youtube.com/watch?v=GMG0a_9-AzU
– Designing and Building Complex Machine Learning Projects – JOSHUA ARVIN LAT Craft Conference 2021 — https://www.youtube.com/watch?v=pcoRxdg6Y9k
– Scale by the Bay Designing and Building Complex Machine Learning Systems and Pipelines — https://www.youtube.com/watch?v=bXlJzOEHmY0
IMPACT 2023 Proceeding Session Video:
To view the proceeding session video you must have a CMG Membership. Sign up today!
For existing members sign in here.
