The BlueHat Podcast
Trailer
Recent Episodes
Ryen Macababbad on How Security Can Empower Productivity
Ryen Macababbad, Principal Security Program Manager at Microsoft joins Nic Fillingham on this week's episode of The BlueHat Podcast. Ryen discusses their career journey, including the return to Microsoft after working in security architecture and customer trust engineering. Ryen shares insights from their time at Hacker Summer Camp 2024 in Las Vegas, emphasizing the importance of creating frictionless security measures that don't hinder productivity. They explain that when security becomes a barrier, users will find workarounds, potentially compromising security. The conversation touches on the evolving relationship between security and productivity teams, highlighting the need for security to be an enabler rather than an obstacle.
TranscriptMichael Howard on Secure by Design vs Secure by Default
Michael Howard, Principal Security Program Manager at Microsoft joins Nic Fillingham on this week's episode of The BlueHat Podcast. Michael shares his journey at Microsoft, starting from his early days in New Zealand as part of a small team of ten. He discusses his extensive career, his contributions to cybersecurity, and his role in the development of essential security books like "Writing Secure Code" and "The Security Development Lifecycle." Michael reflects on the importance of fundamental security principles and how they remain relevant today. He also touches on his recent move within Microsoft to John Lambert's team, where he continues to focus on security culture and education. The conversation delves into the origins of the Blue Hat conference, Michael's experiences at the first event, and the ongoing significance of secure coding practices and mitigations.
TranscriptNavigating AI Safety and Security Challenges with Yonatan Zunger
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.
TranscriptCraig Nelson on Simulating Attacks with Microsoft’s Red Team
Craig Nelson, leader of Microsoft's Red Team joins Nic Fillingham and Wendy Zenone on this week's episode of The BlueHat Podcast. Craig explains how the Red Team simulates attacks on Microsoft's infrastructure to identify vulnerabilities and protect customer data stored in the cloud. He emphasizes the importance of these simulated attacks in preparing for real threats and describes the collaborative efforts with other security teams at Microsoft, such as the Azure penetration testing team and the Microsoft Security Response Center. Craig shares his personal journey into cybersecurity, highlighting his early fascination with cryptography and computer security. He also discusses the unique challenges and strategies of Red Teaming at Microsoft, including the need to influence engineering teams and the importance of systemic thinking to create durable security solutions.
TranscriptUnlocking Backdoor AI Poisoning with Dmitrijs Trizna
Dmitrijs Trizna, Security Researcher at Microsoft joins Nic Fillingham on this week's episode of The BlueHat Podcast. Dmitrijs explains his role at Microsoft, focusing on AI-based cyber threat detection for Kubernetes and Linux platforms. Dmitrijs explores the complex landscape of securing AI systems, focusing on the emerging challenges of Trustworthy AI. He delves into how threat actors exploit vulnerabilities through techniques like backdoor poisoning, using gradual benign inputs to deceive AI models. Dmitrijs highlights the multidisciplinary approach required for effective AI security, combining AI expertise with rigorous security practices. He also discusses the resilience of gradient-boosted decision trees against such attacks and shares insights from his recent presentation at Blue Hat India, where he noted a strong interest in AI security.
Transcript
