*** For educational purposes only ***

DISCLAIMER: This video is for educational and informational purposes only.

The content is intended to demonstrate concepts, techniques, and processes for learning and research purposes. It is not intended to encourage, promote, or facilitate any illegal activity, cyberattack, or unauthorized access to systems.

By watching this video, you agree that you will not use the information to commit any unlawful act. The creator of this content makes no warranty, express or implied, and shall not be liable for any damages arising from the use of the information provided.

This video does not constitute professional advice, and you should consult qualified professionals before applying any techniques shown in a real‑world context.

We talk about the new Anthropic report "Detecting and countering misuse of AI" that was released in September 2026

Gina breaks down new AI attack paths, supply chain risk, vendor pivots, runtime security, and the growing blast radius of autonomous threats. She also explains why having a “human in the loop” is not enough—the real question is where humans should sit in the process so they can provide judgment without becoming bottlenecks.

This is an essential conversation for security professionals, enterprise leaders, and anyone who wants to understand what AI-enabled attacks mean for their organization, data, and family.

Link to Anthropic report: https://www.anthropic.com/threat-intelligence-report-september-2026

We dive into AI-assisted ransomware, ransomware-as-a-service, incident response, offline backups, open-source security risks, threat intelligence, and the growing need for AI-specific security assessments. Fredrick also explains why cybersecurity awareness is struggling to keep pace with AI adoption and what organizations, technical teams, families, and everyday users can do to stay protected.

The conversation also explores AI governance and cybersecurity policy across Africa, including the need for security by design and stronger alignment with emerging standards such as ISO 42001.

John brings 30+ years in cyber, infrastructure, cloud, and digital transformation, plus his perspective as an adjunct faculty member in George Washington University's cyber analytics program. The conversation goes beyond enterprise risk. John and Anmol get into the growing threat to critical infrastructure, including water systems, power grids, and other legacy environments with technical debt and huge attack surfaces. John lays out what state and local leaders need to do first: understand what they have, map the interconnections, modernize where needed, and make AI security a legislative priority instead of an afterthought.

If you care about AI security, cyber policy, critical infrastructure, or the future of education in an AI-driven world, this episode is packed with practical guidance. Essential listening if you want to understand how to keep moving fast with AI without handing over the master key.

Dr. Cuneyt Gurer breaks down why security teams that only focus on the model are missing the bigger picture, and why AI is now colliding with illicit markets, organized crime, and state proxies. Anmol and Dr. Gurer unpack how AI changes the nature of traditional threats. You’ll discover why supply chains matter just as much as prompts, and how sovereign AI is tied to minerals and chip production

Dr. Gurer is a professor of international and security studies at the George C. Marshall European Center for Security Studies, where he designs courses for security professionals and studies how AI intersects with geopolitics, illicit markets, and defense. The opinions reflected in this episode are his own personal views and do not reflect those of any organization.

We talk about the incident where OpenAI broke out of its test environment, impacting Hugging Face, the changing landscape of AI attacks, and tips and tricks on how to get hired in AI security jobs.

Don't miss Emma's upcoming talks at DEF CON’s AI and AppSec villages, where she explores the failures of traditional zero trust and the risks of shadow APIs

Discover how agile methods like Scrum and specific guardrails in agents.md can transform your AI team into a predictable, secure powerhouse. Carlos emphasizes that integrating traditional engineering principles—such as specification-driven development and rigorous governance—is more critical than ever in the age of rapid AI adoption. You’ll learn how to inject discipline into your AI workflows, avoid hallucinations, and maintain human oversight in a landscape pushing towards autonomous decision-making.

In this episode, you’ll learn how privacy-enhancing technologies such as homomorphic encryption and differential privacy are shaping privacy-preserving AI models. See how innovative educational tools like gamified festivals and storytelling are making complex AI and security concepts accessible and engaging for everyone, from legal teams to everyday users.

We break down the evolving landscape of AI regulation, highlighting differences between the EU, US, and Turkey. Understand how the EU’s risk-based approach and the AI Act could impact developers and companies worldwide.

This episode is essential listening for legal professionals, security experts, AI developers, and anyone interested in safeguarding the future of AI. Learn how to transform "boring" privacy and security topics into engaging, impactful experiences via games, stories, and comics.

Yacine shares his journey through cybersecurity and AI research, along with his work on the OWASP Exchange, an initiative helping bridge the gap between security professionals, developers, and AI practitioners. The conversation dives into why AI security is becoming inseparable from API security, especially as AI agents increasingly interact with internal systems, APIs, and sensitive data.

We explore the emerging challenges companies face in securing AI models and autonomous agents, from observability gaps and permission scoping to adversarial machine learning and prompt injection attacks. Yacine explains why AI agents should be treated as non-human identities and how principles like least privilege and security-by-design are becoming essential for modern AI deployments.

The episode also covers real-world security concerns, including supply chain risks in the AI ecosystem and lessons from the recent LiteLLM incident. Along the way, Yacine shares practical advice for engineers, founders, and security teams looking to safely adopt AI while maintaining innovation speed.

Whether you’re building AI products, securing APIs, or simply trying to understand where the future of cybersecurity is headed, this episode offers a grounded and highly practical look into the rapidly evolving world of AI security.

Stay curious, keep experimenting, and learn how security is evolving alongside AI.

Check out this episode for in-depth overview of AI security from a legal perspective.

We explore how neurodiversity contributes valuable strengths to cybersecurity teams, particularly in identifying patterns, managing complexity, and improving resilience in AI-driven environments. The discussion also touches on the realities small businesses face as they adopt AI tools, from governance considerations to everyday security awareness.

Rather than focusing on hype, this episode looks at practical, real-world considerations shaping how AI security is understood and applied across the UK small business landscape. This conversation is for anyone interested in how AI security is evolving in real-world business environments, and the human factors that shape it.

With a background as a classical pianist turned security strategist, and now founder of Cybility Consulting, Michala brings a distinctive, human-centered lens to cybersecurity.

We dive deep into the Companies House breach, which was a devastating breach in the UK, unpacking what happened, where controls and oversight fell short, and why incidents like this highlight the importance of cybersecurity awareness and education. Michala explains why AI can support detection and efficiency, but cannot replace human judgment, especially in complex, high-stakes scenarios. We also talk about accessibility considerations when traveling at airports and navigating security checkpoints which are now augmented by AI.

Grounded in a real incident and expert insight, this episode provides great advice for charities, non-profits, and leaders.

In this episode, you’ll learn why building a strong security culture is essential, how AI can both enhance and complicate penetration testing, and why continuous monitoring and vigilance are the keys to protecting data in a rapidly evolving digital landscape.

Learn about what Quantum computing is, the different kind of QR code vulnerabilities, and the importance of protecting your data.

In this episode of AI Security Update, we sit down with Josh Peltz, VP at Zero Networks and a seasoned cybersecurity leader with 25+ years in tech and over a decade in cybersecurity. Josh brings a unique perspective from the frontlines of sales, strategy, and real-world customer conversations.

Vendors on the expo floor promise faster detection, and sometimes AI security marketing pitches sound the same.

Josh shares what CISOs are really saying in private and his advice on how to create a memorable marketing strategy.

Whether you're interested in developing a powerful marketing strategy or getting an inside scoop on the hidden conversations at RSAC this year, this episode is for you.

In this episode, we sit down with cybersecurity professional Hakeem Thomas, a U.S. military veteran with nearly two decades of experience across penetration testing, digital forensics, incident response, and Zero Trust initiatives.

Hakeem shares a real-world phishing campaign where AI-generated images—built from employee photos—were used to trick staff into clicking. The result? A highly effective social engineering attack that bypassed traditional red flags and exposed just how dangerous AI-powered OSINT has become.

We dive into how attackers are now automating reconnaissance across thousands of sites in minutes, cloning identities, and crafting hyper-personalized attacks that are nearly impossible to detect. From fake baby photos to voice cloning and sock puppet accounts, the threat landscape is evolving faster than most organizations can keep up.

But this isn’t just about tools—it’s about people. Why are these attacks so effective? And what does your digital footprint reveal to someone who knows how to look?

In this episode, we talk with cybersecurity leader Yesenia Yser. Drawing from her work across the open source ecosystem and organizations like the Linux Foundation and Open Source Security Foundation, she breaks down why open source AI models can introduce hidden vulnerabilities. Through her nonprofit, The Lioness Instincts, Yesenia is redefining what security means and teaching women how to protect themselves both physically and digitally, blending cybersecurity with real-world self-defense. In this episode, we break down hidden vulnerabilities, copyright risks, algorithmic bias, and how to protect yourself from AI-driven scams online and in real life.

In this episode, we’re joined by Angela Saccone, Cybersecurity Professional, AI Security Enthusiast, and Podcaster, to explore how AI is reshaping the security landscape across core domains. We break down key concepts in virtual machines, cloud security, and application security, and how these environments are evolving in an AI-driven world.

We also discuss incident response in the context of AI-powered threats and the growing importance of governance.

Using OpenClaw as a real-world anchor, this conversation highlights emerging risks, practical security considerations, and how both practitioners and newcomers can better understand and navigate AI security today.

In this episode, Dd Budiharto, who works as a Chief Security Advisor at Microsoft, dives into the real security challenge most organizations aren’t ready for: agentic AI with identities and access. We break down how “shadow AI employees” are already creeping into enterprises, and what it actually means to secure AI inside enterprise platforms.

The takeaway is simple but urgent: if you’re not managing AI like part of your workforce, you don’t have control, you have exposure.

Disclaimer: All opinions expressed in this episode are the individual opinions of the host and guest featured.

The opinions do not reflect that of any organization.

Resources:

Microsoft Resources:

- https://learn.microsoft.com/en-us/security/security-for-ai/

- https://www.microsoft.com/en-us/security/blog/2026/03/19/new-tools-and-guidance-announcing-zero-trust-for-ai/

- https://learn.microsoft.com/en-us/copilot/microsoft-365/copilot-control-system/security-governance

- https://learn.microsoft.com/en-us/copilot/security/responsible-ai-overview-security-copilot

Other resources:

- https://www.nist.gov/itl/ai-risk-management-framework

- https://www.cisa.gov/resources-tools/resources/ai-data-security-best-practices-securing-data-used-train-operate-ai-systems

In this episode, Omar Sangurima,
Head of Cyber Program Management & Cyber Third-Party Risk at Memorial Sloan Kettering Cancer Center and Anmol Agarwal explore how AI is helping unlock insights in healthcare and improving patient outcomes. They discuss why thoughtful AI regulation is essential, the balance between innovation and privacy, and even how global events like the FIFA World Cup reveal AI’s growing role in society.

Join us for a forward-looking conversation on the opportunities, ethical considerations, and exciting future of AI in healthcare.

The conversation also shifts to the human side of AI in cybersecurity: using AI to prepare conference talks, staying relevant in public speaking, and learning from industry leaders like Caleb Sima and Phillip Wylie. Hernandez highlights the importance of networking within the cybersecurity community and how collaboration often becomes the strongest defense in an AI-driven threat landscape.

They close by discussing data privacy and the global impact of regulations like the General Data Protection Regulation (GDPR), emphasizing why privacy awareness must evolve alongside AI innovation.

This episode blends infrastructure, insight, and community revealing that securing AI is as much about people and principles as it is about technology.

In this episode, Anmol Agarwal talks with Aby Rao — 20 years in cybersecurity and a passion for storytelling — about the unexpected overlap between filmmaking and AI security.

They unpack how AI is reshaping creativity, where automation can dilute originality, and why insider threats and accountability matter more than ever in an AI-driven world.

Because whether you’re directing a film or deploying AI, what you build and how you control it defines the outcome.

Using Star Trek as a playful yet insightful analogy, Kevin explains how AI can be a powerful tool like a calculator for security, but also how risks like prompt injection and data poisoning can cause real damage if left unchecked. They dive into practical ways to apply Zero Trust principles and context to make AI safer and more effective.

Whether you’re defending networks or exploring AI’s role in security, this episode offers actionable insights for using AI responsibly without losing control.

Larci shares practical strategies for incident response and tabletop exercises, explaining how teams can move beyond check-the-box planning and actually prepare for real incidents. The discussion also dives into today’s cybersecurity job market, where AI is screening candidates while job seekers increasingly rely on AI themselves—creating an “AI vs AI” dynamic that’s changing how careers are built and evaluated.

They also explore why community engagement, information sharing, and human judgment remain critical as AI becomes more embedded in security operations

The conversation covers practical AI security best practices, the importance of employee education and monitoring, and how tools like the Software Bill of Materials (SBOM) and the emerging AI Bill of Materials help organizations understand and manage AI risk. Shannon also explores AI security challenges in regulated industries such as healthcare and why responsible AI governance is critical as adoption accelerates.

This episode is essential viewing for CISOs, security leaders, compliance professionals, and anyone navigating AI governance, data protection, and cybersecurity in the age of AI.

The conversation dives into how AI is being used in vulnerability testing and ethical hacking, reinforcing the idea that AI is a powerful tool to augment human expertise, not replace it. They also discuss the importance of securing critical infrastructure, along with key AI security challenges such as data privacy, trust, and the need for continuous human oversight.

Beyond technology, the episode touches on career pathways in cybersecurity, the value of mentorship, and the collaborative, supportive nature of the tech community. It’s an insightful look at how people, skills, and AI come together to shape the future of AI Security.