MLSecOps Podcast
Popular topics
# AI Security
# MLSecOps
# Supply Chain Vulnerability
# AI Risk
# Governance, Risk, & Compliance
# LLM
# Adversarial ML
# Generative AI
# AI/ML Security Vulnerabilities
# Model Provenance
# AI/ML Red Teaming
# Trusted AI
# AdvML
# Prompt Injection
# AI Impact
# ChatGPT
# AI Agents
# Threat Research
# Model Scanning
# huntr
External
Adversarial Robustness for Machine Learning
Hear IBM Principal Research Scientist, Pin-Yu Chen, PhD, discuss compelling themes from his book co-authored with Cho-Jui Hsieh, "Adversarial Robustness for Machine Learning."
# Adversarial ML
# Robustness
# AdvML
# MLSecOps
External
Just How Practical Are Data Poisoning Attacks?
Dr. Florian Tramèr, discusses the practicality of data poisoning attacks, the intersection of AdvML and MLSecOps, and themes from his preprint, "Poisoning Web-Scale Training Datasets is Practical."
# Supply Chain Vulnerability
# Adversarial ML
# MLSecOps
External
MLSecOps: Securing AIML Systems in the Age of Information Warfare
A deep dive with former political operative and author of "Securing AIML Systems in the Age of Information Warfare," Disesdi Susanna Cox, founder of AnglesofAttack.io.
# Adversarial ML
# AdvML
# Supply Chain Vulnerability
# MLSecOps
# AI Security
External
Unpacking AI Bias: Impact, Detection, Prevention, and Policy
This episode delves into the topics of Trusted and Ethical AI under the MLSecOps umbrella, highlighting the importance of conversation around AI bias and building more ethical and fair AI/ML systems.
# Trusted AI
# Ethical AI
# AI Impact
# Governance, Risk, & Compliance
# MLSecOps
# AI Bias
# Fairness
# Cari Miller
External
MITRE ATLAS - Defining the ML System Attack Chain & Needing MLSecOps
Dr. Christina Liaghati discusses various AI security topics, including the contrasts between the MITRE ATT&CK matrix focused on traditional cybersecurity, and the newer AI-focused MITRE ATLAS matrix.
# Adversarial ML
# AdvML
# Supply Chain Vulnerability
# Governance, Risk, & Compliance
# MLSecOps
# MITRE ATLAS
External
MLSecOps: Red Teaming, Threat Modeling, and Attack Methods of AI Apps
Johann discusses how to apply a traditional security engineering mindset and red team approach to analyzing the AI/ML attack surface.
# Supply Chain Vulnerability
# Model Scanning
# AI/ML Red Teaming
# Adversarial ML
# Prompt Injection
# LLM
# Threat Research
# MLSecOps
External
AI Audits: Uncovering Risks in ML Systems
Shea Brown, PhD explores the “W’s” (who, when, why, what) with the MLSecOps Podcast, as well as practices related to AI and algorithm audits & regulatory compliance.
# AI Audit
# Governance, Risk, & Compliance
# Trusted AI
# AI Bias
# Fairness
# Explainability
# MLSecOps
# AI Risk
External
ML Security: AI Incident Response Plans and Enterprise Risk Culture
Patrick Hall discusses the importance of “responsible AI” implementation and risk management, as well as real-world incidents resulting from insufficient AI/ML risk assessments and audits.
# Governance, Risk, & Compliance
# AI Audit
# Transparency
# Explainability
# Model Provenance
# MLSecOps
# AI Risk
External
Responsible AI: Defining, Implementing, and Navigating the Future
Diya Wynn explores the definition of "Responsible AI" as an operating approach focused on minimizing unintended impact and maximizing benefits. She also discusses GenAI's potential to perpetuate bias.
# Trusted AI
# Ethical AI
# AI Bias
# Fairness
# Generative AI
# MLSecOps
# Responsible AI
# Explainability
External
Indirect Prompt Injections and Threat Modeling of LLM Applications
This episode dives into Kai’s research, real world implications of AI security breaches, LLM apps in everyday workflows and related risks, mitigation strategies, and the future of AI/ML red teaming.
# AdvML
# Prompt Injection
# Indirect Prompt Injection
# LLM
# Generative AI
# AI Security
# Threat Research
# MLSecOps
# Large Language Model
# ChatGPT
External
Everything You Need to Know About "Hacker Summer Camp"
Everything You Need to Know About "Hacker Summer Camp"
# Adversarial ML
# AdvML
# Ethical Hacking
# Threat Research
# Vulnerability Reporting
# MLSecOps
# DEF CON
# Black Hat
# AI/ML Red Teaming
# huntr
External
Navigating the Challenges of LLMs: Guardrails AI to the Rescue
Meet Shreya Rajpal, the creator of Guardrails AI; designed to to enhance the security and reliability of LLM applications through output validation, input validation, and domain-specific safeguards.
# LLM
# AI Security
# Indirect Prompt Injection
# Prompt Injection
# MLSecOps
# ChatGPT
# Generative AI
# Large Language Model
External
The Evolved Adversarial Machine Learning Landscape
Explore the National Institute of Standards and Technology (NIST) white paper, "Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations" with co-author, Apostol Vassilev.
# Adversarial ML
# AdvML
# AI/ML Security Vulnerabilities
# Supply Chain Vulnerability
# AI Security
# MLSecOps
# NIST
External
The Intersection of MLSecOps and DataPrepOps
What is DataPrepOps? Dr. Jennifer Prendki explains, as well as discusses data quality, security risks for data scientists, and data curation's role in helping to mitigate security risks in ML models.
# Supply Chain Vulnerability
# Model Provenance
# Data Science
# Governance, Risk, & Compliance
# MLSecOps
# DataPrepOps
External
Privacy Engineering: Safeguarding AI & ML Systems in a Data-Driven Era
Author of "Practical Data Privacy," Katharine Jarmul, discusses GDPR, general data privacy and security risks associated with ML models, and more specific cases like with OpenAI's ChatGPT.
# AI Security
# Privacy
# AI Risk
# Data Science
# Large Language Model
# ChatGPT
# Generative AI
# MLSecOps
External
Exploring AI/ML Security Risks at Black Hat USA 2023
Exploring AI/ML Security Risks at Black Hat USA 2023 with Dr. Christina Liaghati, Daniel Miessler, Adam Shostack, and Phillip Wylie.
# Supply Chain Vulnerability
# Model Provenance
# AI Agents
# Trusted AI
# Governance, Risk, & Compliance
# Adversarial ML
# AdvML
# API Security
# Application Security
# AI Security
# AI/ML Security Vulnerabilities
# Generative AI
# LLM
# ChatGPT
# MLSecOps
# Black Hat
# DEF CON
External
ML Model Fairness: Measuring and Mitigating Algorithmic Disparities
Fairness in AI: what does that actually mean? Nick Schmidt discusses key principles of model governance and fairness, from things like accountability and ownership, to model deployment and monitoring.
# AI Audit
# AI Bias
# AI Impact
# AI Risk
# Ethical AI
# Explainability
# Fairness
# Governance, Risk, & Compliance
# Responsible AI
# Transparency
# Trusted AI
# MLSecOps
External
Securing the AI Lifecycle with MLSecOps: People, Process, and Technology
Themes from Rob's presentation "Attacking and Protecting Artificial Intelligence," including security best practices in AI production compared to traditional software development, and ISO 5338.
# Adversarial ML
# AdvML
# AI Security
# AI/ML Security Vulnerabilities
# MLSecOps
# Model Provenance
# Application Security
# API Security
# Supply Chain Vulnerability
# Generative AI
# LLM
# Large Language Model
# Data Science
External
AI/ML Security in Retrospect: Insights from Season 1 of The MLSecOps Podcast (Part 1)
Revisiting clips about adversarial ML, how malicious actors can use AI to fool machine learning systems into making incorrect decisions; supply chain vulnerabilities, AI/ML red teaming, and more!
# Adversarial ML
# AdvML
# AI Risk
# AI Security
# NIST
# Robustness
# MITRE ATLAS
# LLM
# Generative AI
# Large Language Model
# Supply Chain Vulnerability
# MLSecOps
# Indirect Prompt Injection
# Prompt Injection
External
AI/ML Security in Retrospect: Insights from Season 1 of The MLSecOps Podcast (Part 2)
Show highlights: defining responsible AI, bias detection and prevention, model fairness, AI audits, incident response plans, privacy engineering, and the significance of data in MLSecOps.
# Trusted AI
# Responsible AI
# AI Bias
# Fairness
# AI Audit
# Explainability
# Transparency
# AI Risk
# Privacy
# Data Science
# MLSecOps
External
Cybersecurity of Tomorrow: Exploring the Future of Security and Governance for AI Systems
Martin Stanley, CISSP, discusses CISA initiatives, partnering with NIST to promote adoption of the AI Risk Management Framework, AI security and governance, and much more!
# AI Impact
# AI Risk
# AI Security
# CISA
# NIST
# AI/ML Security Vulnerabilities
# Governance, Risk, & Compliance
# MLSecOps
# Supply Chain Vulnerability
External
From Risk to Responsibility: Violet Teaming in AI
Alexander Titus discusses themes from his forward-thinking paper, "The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward"
# Violet Teaming
# MLSecOps
# Trusted AI
# Biotechnology
# AI Impact
# AI Risk
# Life Sciences
# Governance, Risk, & Compliance
External
Real-World Adversarial ML Attack Risks and Effective Management: Robustness vs. Non-ML Mitigations
Drew Farris (Principal, Booz Allen) and Edward Raff (Chief Scientist, Booz Allen) to discuss themes from their paper, "You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks
# Adversarial ML
# Robustness
# AI Risk
# AI Security
# MLSecOps
# AdvML
# Supply Chain Vulnerability
# Threat Research
External
Risk Management and Enhanced Security Practices for AI Systems
Learn about the Databricks AI Security Framework, building the MLSecOps dream team, challenges that CISOs and business leaders face with AI risk assessments, and much more!
# Adversarial ML
# AdvML
# Supply Chain Vulnerability
# Model Provenance
# AI Impact
# AI Risk
# AI Security
# AI/ML Security Vulnerabilities
# Governance, Risk, & Compliance
# MLSecOps
# Model Scanning
# Trusted AI
External
Secure AI Implementation and Governance
Insights from Nick James (WhitegloveAI) regarding AI Governance, ISO/IEC 42001:2023-Information Technology, Artificial Intelligence Management System, and continuous improvement for AI security.
# Governance, Risk, & Compliance
# MLSecOps
# AI Risk
# AI Security
# AI Impact
# Trusted AI
External
Finding a Balance: LLMs, Innovation, and Security
Sandy Dunn discusses the AI attack surface, the OWASP LLM AI Security & Governance Checklist, AI/ML Bill of Materials, and maintaining equilibrium between innovation and security for AI.
# AdvML
# Adversarial ML
# AI Agents
# AI Security
# AI Risk
# Governance, Risk, & Compliance
# AI Impact
# Application Security
# ChatGPT
# LLM
# Generative AI
# Supply Chain Vulnerability
# Large Language Model
# Model Provenance
# MLSecOps
External
Securing AI: The Role of People, Processes & Tools in MLSecOps
Explore concepts related to building security into the AI/ML lifecycle from end to end via MLSecOps practices.
# AI Risk
# AI Security
# CISA
# Data Science
# Model Provenance
# Model Scanning
# MLSecOps
# Supply Chain Vulnerability
# Governance, Risk, & Compliance
External
AI Threat Research: Spotlight on the Huntr Community
Learn about the world’s first bug bounty platform for AI & machine learning, huntr, including how to get involved!
# Adversarial ML
# AI Security
# AI/ML Red Teaming
# Bug Bounty
# DEF CON
# Ethical Hacking
# huntr
# Supply Chain Vulnerability
# MLSecOps
# Threat Research
# Vulnerability Reporting
External
ReDoS Vulnerability Reports: Security Relevance vs. Noisy Nuisance
Delve into a hot topic in the bug bounty world: Regular Expression Denial of Service reports. Inspired by reports submitted by the huntr AI/ML bug bounty community and blog by OSS expert, William.
# OSS
# ReDoS
# huntr
# Bug Bounty
# Vulnerability Reporting
# MLSecOps
# Supply Chain Vulnerability
# AI Security
# API Security
# Application Security
# Ethical Hacking
External
Evaluating RAG and the Future of LLM Security: Insights with LlamaIndex
In this episode of the MLSecOps Podcast, host Neal Swaelens, along with co-host Oleksandr Yaremchuk, sit down with special guest Simon Suo, co-founder and CTO of LlamaIndex.
# LLM
# Generative AI
# Prompt Injection
# Adversarial ML
# Privacy
# AI Security
# API Security
# RAG
# Retrieval-Augmented Generation
# MLSecOps