PyData Cambridge - 48th Meetup

Agenda

📣📣We are happy to announce the 48th PyData Cambridge Meetup!📣📣

Agenda:

18:45 - 🚪 Doors open (Please do not arrive earlier)

19:00 - ▶️ Introduction

19:15 - 🗣 Practical Detection Engineering in Cybersecurity using Polars - Chris Lo**.**

19:50 - 🥤 Q&A and Networking - drinks and snacks provided

20:15 - 🗣 Full-reference image quality assessment for reconstruction algorithms*- Anna Breger***.**

20:50ish - 🍻 End (Pub - Station Tavern, Station Square, map here).

This event is sponsored by the Raspberry Pi Foundation.

----------------------------------------------------------------

Abstract 1

This talk is an introduction to detection engineering using Polars, which is a new blazing fast DataFrame library built on Rust. This talk uses real data from AWS CloudTrail and a live code-along with Jupyter notebooks to demonstrate the basics of cyber threat hunting.

We end with a deeper dive into the Polars expressions APIs and compare it to other query languages from the cybersecurity world (e.g. Kusto Query Language).

Whether you are a data engineer with interest in cybersecurity or a cybersecurity professional looking to learn a new data tool, there's something in this talk for you.

Speaker 1: Chris Lo

Chris is the co-founder of Tracecat: a Y Combinator backed cybersecurity startup. Tracecat is an AI-native monitoring platform designed to hunt multistage attacks in the Cloud. In his past life, Chris was a data engineer in PwC building ML models to fight cyber crime across fintech and crypto.

----------------------------------------------------------------
Abstract 2

When evaluating novel imaging algorithms in a full reference (FR) setting (e.g. reconstruction with phantom data), the problem of image quality assessment translates into comparing two images. Where specialised experts know what to look for, scientists/engineers do often not have this expertise and rely on automated quantification. The commonly used FR-IQ methods have been developed and optimized for natural images and cannot be translated directly to medical imaging tasks. In this talk I will give a short introduction to IQ assessment and provide examples of failure when applying standard FR-IQ measures to varied medical imaging tasks and discuss alternatives and suggestions for future improvements.

Speaker 2: Anna Breger

Our next speaker - Anna Breger is a senior postdoctoral researcher in the Cambridge Image Analysis Group at the DAMTP, University of Cambridge (UK), and PI of the iDeal research project, focusing on image data visualisation and evaluation, at the Medical University of Vienna. She's a member of the global COVID-19 AIX-COVNET collaboration where she is focusing on X-Ray data. Her current main interests are applications of mathematical image processing in medical problems and beyond, including research on data representations, dimension reduction and image quality assessment.
----------------------------------------------------------------

Code of Conduct

PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form.

The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behaviour of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen (leah@numfocus.org) or organizers.