The BlueHat Podcast

Yonatan Zunger, CVP of AI Safety & Security at Microsoft joins Nic Fillingham and Wendy Zenone on this week's episode of The BlueHat Podcast. Yonatan explains the distinction between generative and predictive AI, noting that while predictive AI excels in classification and recommendation, generative AI focuses on summarizing and role-playing. He highlights how generative AI's ability to process natural language and role-play has vast potential, though its applications are still emerging. He contrasts this with predictive AI's strength in handling large datasets for specific tasks. Yonatan emphasizes the importance of ethical considerations in AI development, stressing the need for continuous safety engineering and diverse perspectives to anticipate and mitigate potential failures. He provides examples of AI's positive and negative uses, illustrating the importance of designing systems that account for various scenarios and potential misuses.      In This Episode You Will Learn:       How predictive AI anticipates outcomes based on historical data  The difficulties and strategies involved in making AI systems safe and secure from misuse  How role-playing exercises help developers understand the behavior of AI systems    Some Questions We Ask:        What distinguishes predictive AI from generative AI?  Can generative AI be used to improve decision-making processes?  What is the role of unit testing and test cases in policy and AI system development?    Resources:   View Yonatan Zunger on LinkedIn      View Wendy Zenone on LinkedIn   View Nic Fillingham on LinkedIn    Related Microsoft Podcasts:     Microsoft Threat Intelligence Podcast   Afternoon Cyber Tea with Ann Johnson   Uncovering Hidden Risks       Discover and follow other Microsoft podcasts at microsoft.com/podcasts

In this episode of The BlueHat Podcast, hosts Nic Fillingham and Wendy Zenone are joined by Johann Rehberger, security expert and Red Team director at Electronic Arts. Johann shares his career journey through roles at Microsoft, Uber, and EA, highlighting his expertise in red teaming and cybersecurity. Johann shares the inspiration behind his book on Red Team strategies and discusses his BlueHat 2024 talk on prompt injection vulnerabilities, a critical and evolving AI security challenge. Johann breaks down the distinction between prompt injection and jailbreaking, offering insights into the potential risks, including data exfiltration and system unavailability, and emphasizes the importance of securing Red Teams themselves.      In This Episode You Will Learn:     Why AI tools should have stricter default settings to control what kind of outputs they generate  The importance of reading technical documentation to understand how AI systems are built  Why developers should implement stronger filters for what tokens are allowed to be emitted by LLMs    Some Questions We Ask:    How are prompt injection and SQL injection similar, and how are they different?  What is AI spyware, and how does it exploit memory tools in ChatGPT?  Does AI jailbreaking access the LLM’s core system like iPhone jailbreaking does the OS?         Resources:       View Johann Rehberger on LinkedIn   View Wendy Zenone on LinkedIn    View Nic Fillingham on LinkedIn      Related Microsoft Podcasts:       Microsoft Threat Intelligence Podcast    Afternoon Cyber Tea with Ann Johnson    Uncovering Hidden Risks          Discover and follow other Microsoft podcasts at microsoft.com/podcasts

In this episode of The BlueHat Podcast, hosts Nic Fillingham and Wendy Zenone present an insightful address by Corporate Vice President and Head of Product for Microsoft's Developer Division, Amanda Silver. Amanda discusses the importance of securing the software supply chain and Microsoft's efforts to protect the open-source ecosystem. She introduces the Secure Software Supply Chain Consumption Framework (S2C2F), a model for tracking and defending against vulnerabilities in open-source dependencies. Silver highlights tools like Dependabot and improvements in NuGet to help developers address security issues seamlessly. She also shares a case study on the "XZ" supply chain attack, underscoring the need for a security mindset in tech culture. Silver closes by urging listeners to adopt a proactive approach to cybersecurity, emphasizing that attacks are inevitable.       Resources:    View Amanda Silver on LinkedIn      View Wendy Zenone on LinkedIn    View Nic Fillingham on LinkedIn      Related Microsoft Podcasts:       Microsoft Threat Intelligence Podcast    Afternoon Cyber Tea with Ann Johnson    Uncovering Hidden Risks          Discover and follow other Microsoft podcasts at microsoft.com/podcasts    The BlueHat Podcast is produced by Microsoft and distributed as part of N2K media network.

In episode 41 of The BlueHat Podcast we bring you the BlueHat 2024 day 1 keynote address given by Chris Wysopal, also known as Weld Pond, founder and Chief Security Evangelist at VeraCode, and founding member of the L0pht.     Chris’ talk - A Clash of Cultures Comes Together to Change Software Security - recounts the early days of “hacking” and how the industry evolved to embrace vulnerability discovery and coordinated, responsible disclosure.    Chris presentation provides a fascinating reflection on a tumultuous period for Microsoft around 2001, marked by significant vulnerability discoveries, which ultimately led to the establishment of the Organization for Internet Safety and the consultancy AtStake, transforming the security landscape and professionalizing the role of hackers. Watch Chris’ BlueHat 2024 Day 1 Keynote here: https://youtu.be/w6SAqT4ZQik    Resources:    View Chris Wysopal on LinkedIn      View Wendy Zenone on LinkedIn    View Nic Fillingham on LinkedIn      Related Microsoft Podcasts:       Microsoft Threat Intelligence Podcast    Afternoon Cyber Tea with Ann Johnson    Uncovering Hidden Risks          Discover and follow other Microsoft podcasts at microsoft.com/podcasts