Resource Center

AI Security Interview Series: An Attacker’s Perspective on Defending AI Systems featuring Nick Landers

AI Security: Understanding the Threat Landscape

AI Security Interview Series: Jailbreaking LLMs Automatically featuring Amin Karbasi

Using AI to Jailbreak Large Language Models

Building Your Global AI Policy: Operationalizing International Standards and Regulations

PYMNTS AI Effect Interview

NIST Adversarial ML Taxonomy

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Testing to Red Teaming: What’s Wrong with My AI?

Best Practices for Generative AI Risk Management and Prevention

Generative AI Risk Assessment Llama-2-70b

Navigating the Risk Landscape of Generative AI

Operationalizing the NIST AI RMF

Generative AI Risk Assessment - Falcon-40B-Instruct

Not with a Bug, But with a Sticker: Attacks on ML Systems and What to do About Them

LLM Avalanche Panel: Build & Risks

Testing Generative Models: What You Need to Know

Generative AI Risk Assessment - Dolly 2.0

Generative AI Risk Assessment - Falcon-7B-Instruct

Generative AI Risks

Do Attackers Use Algorithms to Evade ML? An In-the-Wild Phishing Case Study

AI Insecurity - The Unmanaged Risk of Chatbots, GPT-4, and More

Opportunities and Risks of AI in Insurance

“Real Attackers Don’t Compute Gradients,” a fireside chat with the co-authors on adversarial ML

The Importance of AI Risk Management: A Fireside Chat on NIST’s AI RMF Launch

Industry Leaders - ML:Integrity Panel

Machine Learning at Scale - ML:Integrity Panel

Machine Learning Security - ML:Integrity Panel

Hiring and HR - ML:Integrity Panel

Financial Services - ML:Integrity Panel

Instilling Machine Learning Integrity at Mastercard

Governing the AI Lifecycle at CIBC

Insurance - ML:Integrity Panel

Machine Learning Bias and Fairness - ML:Integrity Panel

Open Source LLMs - ML:Integrity Fireside Chat

AI Bill of Rights - ML:Integrity Lightning Talk

Model Quality Beyond F1 Score

Monitoring ML Pipelines at Corelight

Augmenting Omnichannel with AI at L'Oréal

Data Exchange Podcast (Episode 147): Yaron Singer of Robust Intelligence

Eliminating AI Risk—One Model Failure at a Time

Yaron Singer - Catching edge cases in AI

Where is AI going to be in 3 years time? (Yaron Singer)

Why Zillow's AI-based pricing experiment failed (Yaron Singer)

Eliminating AI Failures with the Practical AI Podcast

How to Make Your Machine Learning System Product Ready with Databricks

How To Secure AI Systems feat. Yaron Singer | Stanford MLSys Seminar Episode 30

Algorithms under Attack w/ Pavel Kireyev, Georgina Hall, Kojin Oshiba & Yaron Singer