The AI Summit London 2023


The Major Security Flaws in the ML Lifecycle (and How to Avoid Them)

14 Jun 2023
Practitioners Stage

Machine learning presents a new frontier in security challenges for organisations. In this session, we’ll cover the combination of ML infrastructure, Developer operations and Security policies that must be implemented to tackle this problem. 

Deploying and maintaining machine learning systems has uncovered new challenges, particularly when running at scale and in production. These systems require fundamentally different approaches to the traditional software and DevOps spaces. 

In this talk, Adrian Gonzalez-Martin, Machine Learning Engineer at Seldon, will outline the field of security in data and ML infrastructure including the key challenges and opportunities it presents. He’ll dive into a number of practical examples and the top 10 MLSecOps vulnerabilities. 

He’ll showcase how to leverage cloud-native tooling to mitigate critical security vulnerabilities and will cover essential concepts such as: 

  • Role-based access control for ML system artifacts and resources 
  • Encryption and access restrictions of data in transit and at rest 
  • Best practices for supply chain vulnerability mitigation 
  • Tools for vulnerability scans 
  • Templates that practitioners can introduce to ensure best practices 
Adrian Gonzalez-Martin, Head of ML Serving - Seldon

The 2023 Summit was Proudly Supported By:

Industry Partners


Diamond Sponsors


Platinum Sponsors


Innovation Partner


Gold Sponsors


Silver Sponsors

Bronze Sponsors

Associate Sponsors


Media & Strategic Partners

Hospitality Suite Hosts