EP224 Protecting the Learning Machines: From AI Agents to Provenance in MLSecOps

Guest: Diana Kelley, CSO at Protect AI  Topics: Can you explain the concept of "MLSecOps" as an analogy with DevSecOps, with 'Dev' replaced by 'ML'? This has nothing to do with SecOps, right? What are the most critical steps a CISO should prioritize when implementing MLSecOps within their organization? What gets better  when you do it? How do we adapt traditional security testing, like vulnerability scanning, SAST, and DAST, to effectively assess the security of machine learning models? Can we? In the context of AI supply chain security, what is the essential role of third-party assessments, particularly regarding data provenance? How can organizations balance the need for security logging in AI systems with the imperative to protect privacy and sensitive data? Do we need to decouple security from safety or privacy? What are the primary security risks associated with overprivileged AI agents, and how can organizations mitigate these risks?  Top differences between LLM/chatbot AI security vs AI agent security?  Resources: “Airline held liable for its chatbot giving passenger bad advice - what this means for travellers” “ChatGPT Spit Out Sensitive Data When Told to Repeat ‘Poem’ Forever” Secure by Design for AI by Protect AI “Securing AI Supply Chain: Like Software, Only Not” OWASP Top 10 for Large Language Model Applications OWASP Top 10 for AI Agents  (draft) MITRE ATLAS “Demystifying AI Security: New Paper on Real-World SAIF Applications” (and paper) LinkedIn Course: Security Risks in AI and ML: Categorizing Attacks and Failure Modes

Om Podcasten

Cloud Security Podcast by Google focuses on security in the cloud, delivering security from the cloud, and all things at the intersection of security and cloud. Of course, we will also cover what we are doing in Google Cloud to help keep our users' data safe and workloads secure. We’re going to do our best to avoid security theater, and cut to the heart of real security questions and issues. Expect us to question threat models and ask if something is done for the data subject’s benefit or just for organizational benefit. We hope you’ll join us if you’re interested in where technology overlaps with process and bumps up against organizational design. We’re hoping to attract listeners who are happy to hear conventional wisdom questioned, and who are curious about what lessons we can and can’t keep as the world moves from on-premises computing to cloud computing.