AI CyberSecurity Podcast

Dive deep into the world of AI agent communication with this episode. Join hosts Caleb Sima and Ashish Rajan as they break down the crucial protocols enabling AI agents to interact and perform tasks: Model Context Protocol (MCP) and Agent-to-Agent (A2A).

Discover what MCP and A2A are, why they're essential for unlocking AI's potential beyond simple chatbots, and how they allow AI to gain "hands and feet" to interact with systems like your desktop, browsers, or enterprise tools like Jira. The hosts explore practical use cases, the underlying technical architecture involving clients and servers, and the significant security implications, including remote execution risks, authentication challenges, and the need for robust authorization and privilege management.

The discussion also covers Google's entry with the A2A protocol, comparing and contrasting it with Anthropic's MCP, and debating whether they are complementary or competing standards. Learn about the potential "AI-ification" of services, the likely emergence of MCP firewalls, and predictions for the future of AI interaction, such as AI DNS.

If you're working with AI, managing cybersecurity in the age of AI, or simply curious about how AI agents communicate and the associated security considerations, this episode provides critical insights and context.

Questions asked:

(00:00) Introduction: AI Agents & Communication Protocols

(02:06) What is MCP (Model Context Protocol)? Defining AI Agent Communication

(05:54) MCP & Agentic Workflows: Enabling AI Actions & Use Cases

(09:14) Why MCP Matters: Use Cases & The Need for AI Integration

(14:27) MCP Security Risks: Remote Execution, Authentication & Vulnerabilities

(19:01) Google's A2A vs Anthropic's MCP: Protocol Comparison & Debate

(31:37) Future-Proofing Security: MCP & A2A Impact on Security Roadmaps

(38:00) - MCP vs A2A: Predicting the Dominant AI Protocol

(44:36) - The Future of AI Communication: MCP Firewalls, AI DNS & Beyond

(47:45) - Real-World MCP/A2A: Adoption Hurdles & Practical Examples

In this episode, we sit down with Joseph Thacker, a bug bounty hunter and AI security researcher, to uncover the evolving threat landscape of AI-powered applications and agents. Joseph shares battle-tested insights from real-world AI bug bounty programs, breaks down why AI AppSec is different from traditional AppSec, and reveals common vulnerabilities most companies miss, like markdown image exfiltration, XSS from LLM responses, and CSRF in chatbots.

He also discusses the rise of AI-driven pentesting agents ("hack bots"), their current limitations, and how augmented human hackers will likely outperform them, at least for now. If you're wondering whether AI can really secure or attack itself, or how AI is quietly reshaping the bug bounty and AppSec landscape, this episode is a must-listen.

Questions asked:

(00:00) Introduction

(02:14) A bit about Joseph

(03:57) What is AI AppSec?

(05:11) Components of AI AppSec

(08:20) Bug Bounty for AI Systems

(10:48) Common AI security issues

(15:09) How will AI change pentesting?

(20:23) How is the attacker landscape changing?

(22:33) Where would autimation add the most value?

(27:03) Is code being deployed less securely?

(32:56) AI Red Teaming

(39:21) MCP Security

(42:13) Evolution of pentest with AI

Resources shared during the interview:

- How to Hack AI Agents and Applications

- Critical Thinking Bug Bounty Podcast

- The Rise of AI Hackbots

- Shift - Caido Plugin

- Shadow Repeater

- Nuclei

- Haize Labs

- White Circle AI

- Prompt Injection Primer for Engineers

Can you prove you’re actually human? In a world of AI deepfakes, synthetic identities, and evolving cybersecurity threats, digital identity is more critical than ever.

With AI-generated voices, fake videos, and evolving fraud tactics, the way we authenticate ourselves online is rapidly changing. So, what’s the future of digital identity? And how can you protect yourself in this new era?

In this episode, hosts Caleb Sima and Ashish Rajan is joined by Adrian Ludwig, CISO at Tools For Humanity (World ID project), former Chief Trust Officer at Atlassian, and ex-Google security lead for Android. Together, they explore:

• Why digital identity is fundamentally broken and needs a major reboot
• The rise of AI-powered identity fraud and how it threatens security
• How World ID is using blockchain and biometrics to verify real humans
• The debate: Should we trust governments, companies, or decentralized systems with our identity?
• The impact of GenAI & deepfakes on authentication and online trust

Questions asked:

(00:00) Introduction

(03:55) Digital Identity in 2025

(14:13) How has AI impacted Identity?

(29:33) Trust and Transparency with AI

(32:18) Authentication and Identity

(49:53) What can people do today?

(52:05) Where can people learn about World Foundation?

(53:49) Adoption of new identity protocols

Resources spoken about during the episode:

Tools for Humanity

World.org

AI is evolving fast, and AI agents are the latest buzzword. But what exactly are they? Are they truly intelligent, or just automation in disguise? In this episode, Caleb Sima and Ashish Rajan spoke to Daniel Miessler—a cybersecurity veteran who is now deep into AI security research.

🎙️ In this episode, we cover:

✅ What AI agents really are (and what they’re NOT)

✅ How AI is shifting from searching to making decisions

✅ The biggest myths and misconceptions about AI automation

✅ Why most companies calling their tools “AI agents” are misleading you

✅ How AI agents will impact cybersecurity, business, and the future of work

✅ The security risks and opportunities no one is talking about

Questions asked:

(00:00) Introduction

(03:50) What are AI Agents?

(06:53) Use case for AI Agents

(14:39) Can AI Agents be used for security today?

(22:06) AI Agent’s impact on Attackers and Defenders in Cybersecurity

(37:05) AI Agents and Non Human Identities

(45:22) The big picture with AI Agents

(48:28) Transparency and Ethics for AI Agents

(58:36) Whats exciting about future of AI Agents?

(01:08:00) Would there still be value for foundational knowledge

AI is revolutionizing many things, but how does it impact detection engineering and SOC teams? In this episode, we sit down withDylan Williams, a cybersecurity practitioner with nearly a decade of experience in blue team operations and detection engineering. We speak about how AI is reshaping threat detection and response, the future role of detection engineers in an AI-driven world, can AI reduce false positives and speed up investigations, the difference between automation vs. agentic AI in security and practical AI tools you can use right now in detection & response

Questions asked:

(00:00) Introduction

(02:01) A bit about Dylan Williams

(04:05) Keeping with up AI advancements

(06:24) Detection with and without AI

(08:11) Would AI reduce the number of false positives?

(10:28) Does AI help identity what is a signal?

(14:18) The maturity of the current detection landscape

(17:01) Agentic AI vs Automation in Detection Engineering

(19:35) How prompt engineering is evolving with newer models?

(25:52) How AI is imapcting Detection Engineering today?

(36:23) LLM Models become the detector

(42:03) What will be the future of detection?

(47:58) What can detection engineers practically do with AI today?

(52:57) Favourite AI Tool and Final thoughts on Detection Engineering

Resources spoken about during the episode:

exa.ai - The search engine for AI

Building effective agents (Athropic’s blog different architecture and design patterns for agents)-https://www.anthropic.com/research/building-effective-agents -

Introducing Ambient Agents (LangChain’s blog on Ambient Agents) -https://blog.langchain.dev/introducing-ambient-agents/ -

Jared Atkinson’s Blog on Capability Abstraction -https://posts.specterops.io/capability-abstraction-fbeaeeb26384

LangGraph Studio -https://studio.langchain.com/

n8n -https://n8n.io/

Flowise -https://flowiseai.com/

CrewAI -https://www.crewai.com/

Welcome to 2025! In this episode our hosts Ashish Rajan and Caleb Sima, tackle the pressing question: What should your AI cybersecurity game plan look like this year?

The rapid evolution of agentic AI—where AI agents can perform tasks autonomously—is set to transform businesses, but it comes with unprecedented security challenges. From the resurgence of Identity and Access Management (IAM) to the urgent need for least privilege strategies, this episode captures actionable insights for CISOs and security leaders.

• What is agentic AI and how it may impact businesses?
• Top 3 priorities for building an effective AI security plan.
• The critical role of IAM and least privilege in managing AI agents.
• Real-world examples of how agentic AI will impact operations and security.
• Practical advice on incident response, monitoring, and preparing for AI-driven challenges.

Questions asked:

(00:00) Introduction

(01:59) The current state of AI in Enterprise

(10:22) Different Levels of Agentic AI

(12:05) CISO AI Cybersecurity Game plan for 2025

(15:57) IAM’s fire comeback

(23:11) Top 3 things for AI Cybersecurity Plan

In this episode, to kick of 2025, we dive deep into AI and cybersecurity predictions for 2025 exploring the opportunities, challenges, and trends shaping the future of the industry.

Our hosts, Ashish Rajan and Caleb Sima sat down to discuss the evolution of SOC automation and its real-world impact on cybersecurity, the practical use cases for AI-enhanced security tools in organizations, why data security might be the real winner in 2025, the potential of agentic AI and its role in transforming security operations and predictions for AI-powered startups and their production-ready innovations in 2025.

Questions asked:

(00:00) Introduction

(06:32) Current AI Innovation in Cybersecurity

(21:57) AI Security Predictions for 2025

(25:02) Data Security and AI in 2025

(30:56) The rise of Agentic AI

(35:40) Planning for AI Skills in the team

(42:53) What to ditch from 2024?

(48:00) AI Making Security Predictions for 2025

Host Caleb Sima and Ashish Rajan caught up with experts Daniel Miessler (Unsupervised Learning), Joseph Thacker (Principal AI Engineer, AppOmni) to talk about the true vulnerabilities of AI applications, how prompt injection is evolving, new attack vectors through images, audio, and video and predictions for AI-powered hacking and its implications for enterprise security.

Whether you're a red teamer, a blue teamer, or simply curious about AI's impact on cybersecurity, this episode is packed with expert insights, practical advice, and future forecasts. Don’t miss out on understanding how attackers leverage AI to exploit vulnerabilities—and how defenders can stay ahead.

Questions asked:

(00:00) Introduction

(02:11) A bit about Daniel Miessler

(02:22) A bit about Rez0

(03:02) Intersection of Red Team and AI

(07:06) Is red teaming AI different?

(09:42) Humans or AI: Better at Prompt Injection?

(13:32) What is a security vulnerability for a LLM?

(14:55) Jailbreaking vs Prompt Injecting LLMs

(24:17) Whats new for Red Teaming with AI?

(25:58) Prompt injection in Multimodal Models

(27:50) How Vulnerable are AI Models?

(29:07) Is Prompt Injection the only real threat?

(31:01) Predictions on how prompt injection will be stored or used

(32:45) What’s changed in the Bug Bounty Toolkit?

(35:35) How would internal red teams change?

(36:53) What can enterprises do to protect themselves?

(41:43) Where to start in this space?

(47:53) What are our guests most excited about in AI?

Resources

Daniel's Webpage - Unsupervised Learning

Joseph's Website

In this jam-packed episode, with our panel we explored the current state and future of AI in the cybersecurity landscape. Hosts Caleb Sima and Ashish Rajan were joined by industry leaders Jason Clinton (CISO, Anthropic), Kristy Hornland (Cybersecurity Director, KPMG) and Vijay Bolina (CISO, Google DeepMind) to dive into the critical questions surrounding AI security. We’re at an inflection point where AI isn’t just augmenting cybersecurity—it’s fundamentally changing the game. From large language models to the use of AI in automating code writing and SOC operations, this episode examines the most significant challenges and opportunities in AI-driven cybersecurity. The experts discuss everything from the risks of AI writing insecure code to the future of multimodal models communicating with each other, raising important questions about trust, safety, and risk management. For anyone building a cybersecurity program in 2024 and beyond, you will find this conversation valuable as our panelist offer key insights into setting up resilient AI strategies, managing third-party risks, and navigating the complexities of deploying AI securely. Whether you're looking to stay ahead of AI's integration into everyday enterprise operations or explore advanced models, this episode provides the expert guidance you need

Questions asked:

(00:00) Introduction

(02:28) A bit about Kristy Hornland

(02:50) A bit about Jason Clinton

(03:08) A bit about Vijay Bolina

(04:04) What are frontier/foundational models?

(06:13) Open vs Closed Model

(08:02) Securing Multimodal models and inputs

(12:03) Business use cases for AI use

(13:34) Blindspots with AI Security

(27:19) What is RPA?

(27:47) AI’s talking to other AI’s

(32:31) Third Party Risk with AI

(38:42) Enterprise view of risk with AI

(40:30) CISOs want Visibility of AI Usage

(45:58) Third Party Risk Management for AI

(52:58) Starting point for AI in cybersecurity program

(01:02:00) What the panelists have found amazing about AI

In this episode of the AI Cybersecurity Podcast, Caleb and Ashish sat down with Vijay Bolina, Chief Information Security Officer at Google DeepMind, to explore the evolving world of AI security. Vijay shared his unique perspective on the intersection of machine learning and cybersecurity, explaining how organizations like Google DeepMind are building robust, secure AI systems.

We dive into critical topics such as AI native security, the privacy risks posed by foundation models, and the complex challenges of protecting sensitive user data in the era of generative AI. Vijay also sheds light on the importance of embedding trust and safety measures directly into AI models, and how enterprises can safeguard their AI systems.

Questions asked:

(00:00) Introduction

(01:39) A bit about Vijay

(03:32) DeepMind and Gemini

(04:38) Training data for models

(06:27) Who can build an AI Foundation Model?

(08:14) What is AI Native Security?

(12:09) Does the response time change for AI Security?

(17:03) What should enterprise security teams be thinking about?

(20:54) Shared fate with Cloud Service Providers for AI

(25:53) Final Thoughts and Predictions

What were the key AI Cybersecurity trends at ⁠BlackHat USA⁠? In this episode of the AI Cybersecurity Podcast, hosts ⁠Ashish Rajan⁠ and ⁠Caleb Sima⁠ dive into the key insights from Black Hat 2024. From the AI Summit to the CISO Summit, they explore the most critical themes shaping the cybersecurity landscape, including deepfakes, AI in cybersecurity tools, and automation. The episode also features discussions on the rising concerns among CISOs regarding AI platforms and what these mean for security leaders.

Questions asked:

(00:00) Introduction

(02:49) Black Hat, DEF CON and RSA Conference

(07:18) Black Hat CISO Summit and CISO Concerns

(11:14) Use Cases for AI in Cybersecurity

(21:16) Are people tired of AI?

(21:40) AI is mostly a side feature

(25:06) LLM Firewalls and Access Management

(28:16) The data security challenge in AI

(29:28) The trend with Deepfakes

(35:28) The trend of pentest automation

(38:48) The role of an AI Security Engineer

In this episode of the AI Cybersecurity Podcast, we dive deep into the latest findings from Google's DeepMind report on the misuse of generative AI. Hosts Ashish and Caleb explore over 200 real-world cases of AI misuse across critical sectors like healthcare, education, and public services. They discuss how AI tools are being used to create deepfakes, fake content, and more, often with minimal technical expertise. They analyze these threats from a CISO's perspective but also include an intriguing comparison between human analysis and AI-generated insights using tools like ChatGPT and Anthropic's Claude. From the rise of AI-powered impersonation to the manipulation of public opinion, this episode uncovers the real dangers posed by generative AI in today’s world.

Questions asked:

(00:00) Introduction

(03:39) Generative Multimodal Artificial Intelligence

(09:16) Introduction to the report

(17:07) Enterprise Compromise of GenAI systems

(20:23) Gen AI Systems Compromise

(27:11) Human vs Machine

Resources spoken about during the episode:

Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data

How much can we really trust AI-generated code more over Human generated Code today? How does AI-Generated code compare to Human generated code in 2024? Caleb and Ashish spoke to Guy Podjarny, Founder and CEO at Tessl about the evolving world of AI generated code, the current state and future trajectory of AI in software development. They discuss the reliability of AI-generated code compared to human-generated code, the potential security risks, and the necessary precautions organizations must take to safeguard their systems.

Guy has also recently launched his own podcast with Simon Maple called The AI Native Dev, which you can check out if you are interested in hearing more about the AI Native development space.

Questions asked:

(00:00) Introduction

(02:36) What is AI Generated Code?

(03:45) Should we trust AI Generated Code?

(14:34) The current usage of AI in Code Generated

(18:27) Securing AI Generated Code

(23:44) Reality of Security AI Generated Code Today

(30:22) The evolution of Security Testing

(37:36) Where to start with AI Security today?

(50:18) Evolution of the broader cybersecurity industry with AI

(54:03) The Positives of AI for Cybersecurity

(01:00:48) The startup Landscape around AI

(01:03:16) The future of AppSec

(01:05:53) The future of security with AI

Which AI Security Framework is right for you? As AI is gaining momentum, we are starting to see quite a few frameworks appearing but the question is, which one should you start with and can AI help you decide! Caleb and Ashish tackle this challenge head-on, comparing three major AI security frameworks: Databricks, NIST, and OWASP Top 10. They break down the key components of each framework, discuss practical implementation strategies, and provide actionable insights for CISOs and security leaders. They may have had some help along the way.

Questions asked:

(00:00) Introduction

(02:54) Databricks AI Security Framework (DASF)

(06: 38) Top 3 things from DASF by Claude 3

(07:32) Top 3 things from DASF by ChatGPT

(08:46) DASF Use Case Scenario

(11:01) Thoughts on DASF

(13:18) OWASP Top 10 for LLM Models

(20:12) Google's Secure AI Framework (SAIF)

(21:31) NIST AI Risk Management Framework

(25:18) Claude 3 summarises NIST RMF for 5 year old

(28:00) ChatGPT compares NIST RMF and NIST CSF

(28:48) How do the frameworks compare?

(36:46) Summary of all the frameworks

Resources from this episode:

Databricks AI Security Framework (DASF)

OWASP Top 10 for LLM

NIST AI Risk Management Framework

Google Secure AI Framework

What is the current state and future potential of AI Security? This special episode was recorded LIVE at BSidesSF (thats why its a little noisy), as we were amongst all the exciting action. Clint Gibler, Caleb Sima and Ashish Rajan sat down to talk about practical uses of AI today, how AI will transform security operations, if AI can be trusted to manage permissions and the importance of understanding AI's limitations and strengths.

Questions asked:

(00:00) Introduction

(02:24) A bit about Clint Gibler

(03:10) What top of mind with AI Security?

(04:13) tldr of Clint’s BSide SF Talk

(08:33) AI Summarisation of Technical Content

(09:47) Clint’s favourite part of the talk - Fuzzing

(15:30) Questions Clint got about his talk

(17:11) Human oversight and AI

(25:04) Perfection getting in the way of good

(30:15) AI on the engineering side

(36:31) Predictions for AI Security

Resources from this coversation:

Caleb's Keynote at BSides SF

Clint's Newsletter

Key AI Security takeaways from RSA Conference 2024, BSides SF 2024 and all the fringe activities that happen in SF during that week. Caleb and Ashish were speakers, panelists, participating in several events during that week and this episode captures all the highlights from all the conversations they had and they trends they saw during what they dubbed the "Cybersecurity Fringe Festival” in SF.

Questions asked:

(00:00) Introduction

(02:53) Caleb’s Keynote at BSides SF

(05:14) Clint Gibler’s Bsides SF Talk

(06:28) What are BSides Conferences?

(13:55) Cybersecurity Fringe Festival

(17:47) RSAC 2024 was busy

(19:05) AI Security at RSAC 2024

(23:03) RSAC Innovation Sandbox

(27:41) CSA AI Summit

(28:43) Interesting AI Talks at RSAC

(30:35) AI conversations at RSAC

(32:32) AI Native Security

(33:02) Data Leakage in AI Security

(30:35) Is AI Security all that different?

(39:26) How to filter vendors selling AI Solutions?

How can AI change a Security Analyst's workflow? Ashish and Caleb caught up with Ely Kahn, VP of Product at SentinelOne, to discuss the revolutionary impact of generative AI on cybersecurity. Ely spoke about the challenges and solutions in integrating AI into cybersecurity operations, highlighting how can simplify complex processes and empowering junior to mid-tier analysts.

Questions asked:

(00:00) Introduction

(03:27) A bit about Ely Kahn

(04:29) Current State of AI in Cybersecurity

(06:45) How AI could impact Cybersecurity User Workflow?

(08:37) What are some of the concerns with such a model?

(14:22) How does it compare to a analyst not using this model?

(21:41) Whats stopping models for going into autopilot?

(30:14) The reasoning for using multiple LLMs

(34:24) ChatGPT vs Anthropic vs Mistral

You can discover more about SentinelOne's Purple AI here!

How is AI transforming traditional approaches to offensive security, pentesting, security posture management, security assessment, and even code security? Caleb and Ashish spoke to Rob Ragan, Principal Technology Strategist at Bishop Fox about how AI is being implemented in the world of offensive security and what the right way is to threat model an LLM.

Questions asked:

(00:00) Introductions

(02:12) A bit about Rob Ragan

(03:33) AI in Security Assessment and Pentesting

(09:15) How is AI impacting pentesting?

(14:50 )Where to start with AI implementation in offensive Security?

(18:19) AI and Static Code Analysis

(21:57) Key components of LLM pentesting

(24:37) Testing whats inside a functional model?

(29:37) Whats the right way to threat model an LLM?

(33:52) Current State of Security Frameworks for LLMs

(43:04) Is AI changing how Red Teamers operate?

(44:46) A bit about Claude 3

(52:23) Where can you connect with Rob

Resources spoken about in this episode:

https://www.pentestmuse.ai/

https://github.com/AbstractEngine/pentest-muse-cli

https://docs.garak.ai/garak/

https://github.com/Azure/PyRIT

https://bishopfox.github.io/llm-testing-findings/

https://www.microsoft.com/en-us/research/project/autogen/

What is the current reality for AI automation in Cybersecurity? Caleb and Ashish spoke to Edward Wu, founder and CEO of Dropzone AI about the current capabilities and limitations of AI technologies, particularly large language models (LLMs), in the cybersecurity domain. From the challenges of achieving true automation to the nuanced process of training AI systems for cyber defense, Edward, Caleb and Ashish shared their insights into the complexities of implementing AI and the importance of precision in AI prompt engineering, the critical role of reference data in AI performance, and how cybersecurity professionals can leverage AI to amplify their defense capabilities without expanding their teams.

Questions asked:

(00:00) Introduction

(05:22) A bit about Edward Wu

(08:31) What is a LLM?

(11:36) Why have we not seen entreprise ready automation in cybersecurity?

(14:37) Distilling the AI noise in the vendor landscape

(18:02) Solving challenges with using AI in enterprise internally

(21:35) How to deal with GenAI Hallucinations?

(27:03) Protecting customer data from a RAG perspective

(29:12) Protecting your own data from being used to train models

(34:47) What skillset is required in team to build own cybersecurity LLMs?

(38:50) Learn how to prompt engineer effectively

There is a complex interplay between innovation and security in the age of GenAI. As the digital landscape evolves at an unprecedented pace, Daniel, Caleb and Ashish share their insights on the challenges and opportunities that come with integrating AI into cybersecurity strategies

Caleb challenges the current trajectory of safety mechanisms in technology and how overregulation may inhibit innovation and the advancement of AI's capabilities. Daniel Miessler, on the other hand, emphasizes the necessity of accepting technological inevitabilities and adapting to live in a world shaped by AI. Together, they explore the potential overreach in AI safety measures and discuss how companies can navigate the fine line between fostering innovation and ensuring security.

Questions asked:

(00:00) Introduction

(03:19) Maintaining Balance of Innovation and Security

(06:21) Uncensored LLM Models

(09:32) Key Considerations for Internal LLM Models

(12:23) Balance between Security and Innovation with GenAI

(16:03) Enterprise risk with GenAI

(25:53) How to address enterprise risk with GenAI?

(28:12) Threat Modelling LLM Models