Guest:  <ul> <li><a href= "https://nicholas.carlini.com/">Nicholas Carlini</a>, Research Scientist @ Google </li> </ul> Topics: <ul> <li style="font-weight: 400;" aria-level="1">What is your threat model for a large-scale AI system? How do you approach this problem? How do you rank the attacks?</li> <li style="font-weight: 400;" aria-level="1">How do you judge if an attack is something to mitigate? How do you separate realistic from theoretical?</li> <li style="font-weight: 400;" aria-level="1">Are there AI threats that were theoretical in 2020, but may become a daily occurrence in 2025?</li> <li style="font-weight: 400;" aria-level="1">What are the threat-derived lessons for securing AI?</li> <li style="font-weight: 400;" aria-level="1">Do we practice the same or different approaches for secure AI and reliable AI?</li> <li style="font-weight: 400;" aria-level="1">How does relative lack of transparency in AI helps (or hurts?) attackers and defenders?</li> </ul> Resources: <ul> <li><a href= "https://www.rsaconference.com/USA/agenda/session/Red%20Teaming%20AI%20Systems%20The%20Path%20the%20Prospect%20and%20the%20Perils"> “Red Teaming AI Systems: The Path, the Prospect and the Perils”</a> at RSA 2022</li> <li><a href= "https://blogs.gartner.com/anton-chuvakin/2015/03/03/killed-by-ai-much-a-rise-of-non-deterministic-security/"> “Killed by AI Much? A Rise of Non-deterministic Security!”</a></li> <li><a href= "https://www.google.com/search?tbm=bks&q=adversarial+ML"> Books on Adversarial ML</a></li> </ul>

EP69 Cloud Threats and How to Observe Them

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.