The AI Security Podcast
I missed the boat in computer hacking so now I hack AI instead. This podcast discusses all things at the intersection of AI and security. Hosted by me (Harriet Farlow aka. HarrietHacks) and Tania Sadhani and supported by Mileva Security Labs.
Chat with Mileva Security Labs for your AI Security training and advisory needs: https://milevalabs.com/
Reach out to HarrietHacks if you want us to speak at your event: https://www.harriethacks.com/
Episodes
41 episodes
Agentic AI Security: A Primer
For a while we've been wanting to talk about Agentic AI Security.. the thing is that we could spend multiple episodes talking about it! So we decided to do just that. This is part 1 - a primer - where we talk about exactly what AI agents are an...
•
Season 1
•
Episode 41
•
19:02
How Likely Are AI Security Incidents? Updates From Our Final Report!
Six months ago Tania and I made an episode about the interim report for our AI Security Likelihood Project.. and it is finally time to discuss the final report! You'll see it live at this link shortly: https://www.aisecurityfundamentals.com/
•
Season 1
•
Episode 40
•
31:28
To open or close model weights?
In this episode, Tania and I discuss the debate around closed or open model weights. What do you think?The RAND report we mention: https://www.rand.org/pubs/research_reports/RRA2849-1.html
•
27:52
Creative prompt injection in the wild
In this episode, Tania and I talk through some creative examples of prompt injection/engineering we've seen in the wild.. think prompts hidden in papers, red-teaming and web-scraping.Your Brain on ChatGPT:
•
Season 1
•
Episode 37
•
31:10
Threat intel digest: 23 June 2025
This week we discussed multiple AI vulnerabilities, including Echolink in M365 Copilot, Agent Smith in Langchain, and a SQL injection flaw in Llama Index, all of which have been patched. We also covered a data exposure bug in Asana's MCP server...
•
Season 1
•
Episode 36
•
52:13
AI safety evaluations with Inspect
I'm back from holiday, and this week Tania and I talk about a project she completed as part of the ARENA AI safety curriculum to replicate the findings of evaluations on frontier AI capabilities.Link to reasoning paper: <...
•
Season 1
•
Episode 35
•
32:52
Threat intel digest: 9 June 2025
This week we try a new condensed format for the AI security digest! we covered critical CVEs, including vulnerabilities in AWS MCP, Llama Index, GitHub MCP integration, and tool poisoning attacks. We also reported on malware campaigns using spo...
•
54:57
Threat intel digest: 26 May 2025
Sign up to receive in your inbox: http://eepurl.com/i7RgRMTania Sadhani and Miranda R discussed various AI security topics, including critical CVEs affecting platforms like ChatGPT and Hugging Face,...
•
Season 1
•
Episode 32
•
39:23
AI Vulnerability Research with Aditya Rana
Ever wondered how security vulnerabilities are found in AI? Join us as we chat with Aditya, a Vulnerability Researcher at Mileva Security Labs!
•
Season 1
•
Episode 31
•
38:43
Threat intel digest: 12 May 2025
Sign up to receive in your inbox: http://eepurl.com/i7RgRMThis week we note regular CVEs in AI libraries such as Nvidia TensorFlow and PyTorch. We discuss a novel prompt injection te...
•
Season 1
•
Episode 30
•
48:22
The evolution of data science and AI ethics with Dr Alberto Chierici
This week I'm joined by my friend Alberto, he has an incredible storied career - from data science, insurance, AI risk, advising Tesla.. check out his book here! https://www.amazon.com.au/Ethics-I-Facts-Fictions-Forecasts/dp/1636763650...
•
Season 1
•
Episode 30
•
49:59
Stanford's 2025 AI Index Report
We talk about Stanford Human-Centred AI's latest AI Index report, check it out here: https://hai.stanford.edu/ai-index/2025-ai-index-report
•
Season 1
•
Episode 29
•
35:36
Threat intel digest: 28 April 2025
Did you know we have a fortnightly threat intel newsletter? We decided there was so much good research in there we have to talk about it here! We're joined by threat intel lead Miranda for this fortnight's biggest AI security news, coming out i...
•
Season 1
•
Episode 29
•
37:41
Episode 28: the OWASP ML Security Top 10 with co-lead Shain Singh
My friend Shain joins me on the podcast to talk about his work with the OWASP MLSec Top 10 list and organisational guidance, as well as how he got here!For info about the list and how to contribute, check out the link: https://owasp.org...
•
Season 1
•
Episode 28
•
52:12
Episode 27: all about AI red teaming
This week we talk about AI red teaming.. I can't quite believe we haven't talked about it already! We cover the origins of red teaming in the military, how red teaming is done in cyber security, and the fundamentals of AI red teaming. ...
•
Season 1
•
Episode 27
•
57:30
Episode 26: Microsoft's L33t Sp3ak AI security series ft. me
I didn't manage to get my act into gear to record a fresh episode between getting back from the UK and heading to New Zealand so I've pulled one from the vault.. it's a good one though! A year ago I was interviewed by Microsoft for their AI sec...
•
Season 1
•
Episode 26
•
30:00
Episode 25: conversations at AI UK in London
I didn't want to do a solo episode so instead I enlist free content support by speaking to the vendors at AI UK, run by the Alan Turing Institute, in London! Thanks very much to those people, links below here:Datambit: https://datambit.com/...
•
Season 1
•
Episode 25
•
29:06
Episode 24: examples of AI security incidents, from our Manchester airbnb (but sadly not the hot tub)
We're in Manchester but we can't talk about it much.. so instead we reflect on some of the latest digest incidents (and how we wish the hot tub in our airbnb had water in it).Sign up to the digest here:
•
Season 1
•
Episode 24
•
35:59
Episode 23: the AI lifecycle and what it means for security
In this episode we discuss the AI lifecycle.. we talk through important machine learning stages (training, inference etc), how they apply at the systems levels (agentic systems, APIs etc) and and example in context (facial recognition at airpor...
•
Season 1
•
Episode 23
•
40:16
Episode 22: security careers and content creation with Cyber Expanse host James Webb
In this episode I interview James Webb, host of the Cyber Expanse. We discuss careers at the intersection of AI and cyber security, how to get into the security workforce, and what it's like being 'influencers' (content creators) in the securit...
•
Season 1
•
Episode 20
•
26:31
Episode 21: is AI an optional risk? lessons in risk analysis from a road trip to the Society of Risk Analysis conference
Tania and I went to Melbourne to attend the Society of Risk Analysis Annual General Meeting. What a great group of people.. we learnt so much about risk analysis from these awesome people. We all came from totally different disciplines - climat...
•
Season 1
•
Episode 22
•
31:43
Episode 20: threat intelligence vs vulnerability research in AI
Today I'm joined by Miranda, our threat intel lead at Mileva, to discuss how threat intel and vulnerability research works in the world of AI security. We also recently released a threat digest, sign up here to understand what AI securi...
•
28:45
Episode 19: the TikTok ban (also relevant to DeepSeek?!) part 2
This is part 2 of our discussion on the TikTok ban and its AI security implications. We have not yet recorded a podcast about DeepSeek (look, we're very busy) but you'll find that a lot of the discussion about Chinese national security laws is ...
•
Season 1
•
Episode 19
•
24:07
Episode 18: what is going on with this TikTok ban? Part 1.
We chat about the TikTok ban and its AI security implications. We got so into this topic we had to split it in two parts!The AI security creative comms comp: https://milev.ai/reports/ai-security-communication-competition-2000-in-prizes/<...
•
Season 1
•
Episode 18
•
26:33