Explore the critical distinction between model robustness and security in this thought-provoking 55-minute conference talk from BSidesLV 2022. Delve into Sven Cattell's expert analysis of why robust machine learning models don't necessarily equate to secure systems. Gain valuable insights into the potential vulnerabilities that persist even in seemingly robust AI models and learn strategies to enhance true security in machine learning applications.
Overview
Syllabus
GT - Model Robustness Isn't Security
Taught by
BSidesLV
Related Courses
-
Security and Auditing in Ethereum
-
Your Model Isn't That Special - Zero to Malware Model in Not Much Code and Where the Real Work Lies
-
RAB - Provable Robustness Against Backdoor Attacks
-
Making & Breaking Machine Learning Anomaly Detectors in Real Life
-
Reduce, Reuse and Recycle ML Solutions for Security
-
Security AI in the Real World - Lessons Learned from Building Practical Machine Learning Systems Deployed to Hundreds of Thousands of Networks
