Published Mar 16, 2021

#48 Machine Learning Security - Andy Smith

Explore the intersection of machine learning and security with expert Andy Smith as he delves into the STRIDE methodology and essential measures for safeguarding ML DevOps architectures against cyber threats, emphasizing threat modeling, adversarial examples, and the complexities of secure development.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

#040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr)
Answers 383 questions
Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)
Answers 383 questions
#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)
Answers 383 questions
Jordan Edwards: ML Engineering and DevOps on AzureML
Answers 383 questions
Kaggle, ML Community / Engineering (Sanyam Bhutani)
Answers 383 questions
#52 - Unadversarial Examples (Hadi Salman, MIT)
Answers 383 questions
#57 - Prof. Melanie Mitchell - Why AI is harder than we think
Answers 383 questions
Prof. Melanie Mitchell 2.0 - AI Benchmarks are Broken!
Answers 383 questions
047 Interpretable Machine Learning - Christoph Molnar
Answers 383 questions
#65 Prof. PEDRO DOMINGOS [Unplugged]
Answers 383 questions
#92 - SARA HOOKER - Fairness, Interpretability, Language Models
Answers 383 questions
#86 - Prof. YANN LECUN and Dr. RANDALL BALESTRIERO - SSL, Data Augmentation, Reward isn't enough [NEURIPS2022]
Answers 383 questions
#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!
Answers 383 questions
#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS
Answers 383 questions
#045 Microsoft's Platform for Reinforcement Learning (Bonsai)
Answers 383 questions

Dexa/Machine Learning Street Talk (MLST)

#48 Machine Learning Security - Andy Smith

Topics covered

Popular Clips

ML Security Fundamentals

Threat Modeling Exercise

System Security Insights

ML Threat Vectors

Machine Learning Security

Cybersecurity Threat Modeling

Risk Management and Threat Modeling

Unpredictability in Machine Learning

ML DevOps Insights

Secure Development Insights

Simplifying Cybersecurity

Episode Highlights

Threat Modeling Process

ML DevOps Security

Related Episodes

#040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr)

Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)

#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)

Jordan Edwards: ML Engineering and DevOps on AzureML

Kaggle, ML Community / Engineering (Sanyam Bhutani)

#52 - Unadversarial Examples (Hadi Salman, MIT)

#57 - Prof. Melanie Mitchell - Why AI is harder than we think

Prof. Melanie Mitchell 2.0 - AI Benchmarks are Broken!

047 Interpretable Machine Learning - Christoph Molnar

#65 Prof. PEDRO DOMINGOS [Unplugged]

#92 - SARA HOOKER - Fairness, Interpretability, Language Models

#86 - Prof. YANN LECUN and Dr. RANDALL BALESTRIERO - SSL, Data Augmentation, Reward isn't enough [NEURIPS2022]

#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!

#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS

#045 Microsoft's Platform for Reinforcement Learning (Bonsai)

#48 Machine Learning Security - Andy Smith

Topics covered

Popular Clips

Episode Highlights

Threat Modeling ProcessAndy Smith discusses the application of the STRIDE methodology in identifying cybersecurity threats within ML DevOps architectures. He emphasizes the importance of understanding threat vectors, including adversarial examples, to enhance system security.

Threat Modeling Process

ML DevOps Security

Related Episodes