All Episodes

How to get hired in AI security

getting talks accepted into conferences! tips and tricks

Do we need to secure model weights?

Model Context Protocol and Agent 2 Agent 🤖🕵️

Agentic AI Security | case studies by Microsoft, OWASP

a hacky christmas message

Three Black Hat talks at just 18! My interview with Bandana Kaur.

Effective Altruism and AI with Good Ancestors CEO Greg Sadler | part 2

AI Safety with CEO of Good Ancestors Greg Sadler | part 1

The United States AI Action Plan | will they win the AI race against China? 🤔

AI Security vs Application Security

Agentic AI Security: A Primer

How Likely Are AI Security Incidents? Updates From Our Final Report!

To open or close model weights?

Creative prompt injection in the wild

Threat intel digest: 23 June 2025

AI safety evaluations with Inspect

Threat intel digest: 9 June 2025

Threat intel digest: 26 May 2025

AI Vulnerability Research with Aditya Rana

Threat intel digest: 12 May 2025

The evolution of data science and AI ethics with Dr Alberto Chierici

Stanford's 2025 AI Index Report

Threat intel digest: 28 April 2025

Episode 28: the OWASP ML Security Top 10 with co-lead Shain Singh

Episode 27: all about AI red teaming

Episode 26: Microsoft's L33t Sp3ak AI security series ft. me

Episode 25: conversations at AI UK in London

Episode 24: examples of AI security incidents, from our Manchester airbnb (but sadly not the hot tub)

Episode 23: the AI lifecycle and what it means for security

Episode 22: security careers and content creation with Cyber Expanse host James Webb

Episode 21: is AI an optional risk? lessons in risk analysis from a road trip to the Society of Risk Analysis conference

Episode 20: threat intelligence vs vulnerability research in AI

Episode 19: the TikTok ban (also relevant to DeepSeek?!) part 2

Episode 18: what is going on with this TikTok ban? Part 1.

Episode 17: 30 lessons at 30 (AI security edition)

Episode 16: our top 3 AI security trends to start off 2025

Episode 15: you didn't get enough of GRC last time with Annie-Mei - Part 2

Episode 14: the AI Security Likelihood Project - Interim report and dataset now out!

Episode 13: what on earth is GRC with Annie-Mei Forster Part 1

Episode 12: from data analytics to start-up founder with Howjer Gu

Episode 11: the Mileva backstory.. also Harriet is in VOGUE?!

Episode 10: how to up-skill in AI security

Episode 9: why did California Governor Newsom veto the AI regulation bill and what other bills were passed?

BONUS: how are threat actors using language models?

Episode 7: Is AI Security a subset of Cyber Security with AI security researcher Miranda

BONUS: we rode a Waymo and chat about the impact of automation

Episode 5: hacking the TikTok dance filter and facial recognition models at BSides Canberra and Singapore

Episode 4: reflections on hacker summer camp (BSides LV, DEF CON 32) and San Francisco

BONUS: get hyped for hacker summer camp 2024 - BSides Las Vegas, Black Hat and DEF CON!!

Episode 2: how is AI security different to AI safety and cyber security?

Episode 1: what is AI security.. and who are we??