Sign up to receive in your inbox: http://eepurl.com/i7RgRM

This week we note regular CVEs in AI libraries such as Nvidia TensorFlow and PyTorch. We discuss a novel prompt injection technique called "policy puppetry", along with malware dispersal through fake AI video generators and Meta's release of an open-source AI security tool set including Llama Firewall. We also covered Israel's experimental use of AI in warfare, Russia's AI-enabled drones in Ukraine, China's crackdown on AI misuse, Dreadnode's research on AI in red teaming, geolocation doxing via multimodal LLMs, safety research on autonomous vehicle attacks targeting inference time, Config Scan for analyzing malicious configurations on Hugging Face, Spotlight as a physical solution against deepfakes, and Reply Bench for benchmarking autonomous replication of LLM agents.

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

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 security space.

This episode also has a video equivalent at Harriet Hacks on YouTube, and will have a companion episode on James' YouTube channel as well.

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 - climate, biosecurity, technology - but everyone working in risk has the same challenges!
They were also a great group of people to go out for cocktails with (we had a few).

contact@mileva.com.au

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 security incidents and research are happening in the wild: http://eepurl.com/i7RgRM

contact@mileva.com.au

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 relevant and echoes those same conversations.

Links discussed:

The Infographic: https://newsroom.tiktok.com/en-au/comparative-study-of-social-media-data-collection-practices-au?utm_source=chatgpt.com

Bing vs Google: https://searchengineland.com/google-bing-is-cheating-copying-our-search-results-62914

Reach out at contact@mileva.com.au.

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/

Sign up to our new threat digest:  

http://eepurl.com/i7RgRM 

Get in touch with us at contact@mileva.com.au.

Harriet turned 30 recently and decided to try this trend - but AI security edition! We talk through 30 lessons - AI, security and life.

Contact us at contact@mileva.com.au

Welcome to the AI security podcast! We decided to rebrand and claim this space since no-one else has taken it! We're looking forward to being your go-to podcast for AI security news, research and casual yaps.

In this episode Tania and I each discuss our top three trends in AI security and AI for security as we enter 2025.

Links discussed:
Cyber risk management podcast: https://open.spotify.com/show/43k7780x6wSvKCq75StIsM
About the number 2025: https://mindyourdecisions.com/blog/2025/01/02/5-fun-facts-about-2025-you-probably-didnt-know/
Our AI security research: https://aisecurityfundamentals.com/

Reach out to Mileva at contact@milevalabs.com

We continue our discussion on key trends in GRC and its intersection with AI!

Annie-Mei is also about to launch her own podcast and I highly recommend you check it out if you want more no-nonsense content and advice about the cyber space.

This week we released the interim report and subset of the AI incident database for the AI Security Likelihood research Tania has been working on! We chat through the motivations for the project, our initial insights and takes, and where we hope to take it next. Now we want your input! Check it out at aisecurityfundamentals.com and let us know if you have insights on the risk modelling, AI incidents, or access to data/collaborations that could make this project even better.
(If you don't want to hear us talk about our Christmas party skip to around 8 minutes in).

Big thanks to Foresight for funding this research, and our collaborators at the Australian National University and University of New South Wales.

We mention this book, How to Measure Anything in Cyber Security and recommend giving it a read: https://www.oreilly.com/library/view/how-to-measure/9781119892304/cover.xhtml

Today we chat to my good friend Annie-Mei about GRC (governance, risk and compliance). She is a senior GRC consultant with a background in journalism! We discuss her career journey and an overview of what on earth GRC is.

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

This time we sit down with Howjer Gu, Founder of Planoverse, a start-up in our stream within the UNSW 10x accelerator! Fun fact - Howjer and I used to work together at Deloitte back in 2016 and couldn't believe it when we ran into each other during the application process. Howjer has a background in data analytics and recently founded Planoverse, which is like a digital twin for grocery stores. Learn about his start-up journey and the importance of data.

Planoverse: https://www.planoverse.com.au/

2024 has seen a lot of change for Mileva.. and we often get people asking about what we're doing and we got here, so this time Tania interviews Harriet about starting Mileva! We know lots of our audience are curious about starting a business and the different trade-offs that entails (quitting your full time job, looking for funding, services vs products, when is the right time) so we address some of these questions. We also talk about our experience in the UNSW 10x accelerator (hint: I'll be interviewing some of these founders in upcoming episodes!)
Oh also Harriet somehow ended up in Vogue!

In this episode Tania and I chat through how we learnt about AI security and adversarial machine learning, and how you can too! 

Some resources we mention:
- Crash Course AI https://thecrashcourse.com/topic/ai/
- 3 Blue 1 Brown https://www.youtube.com/c/3blue1brown
- Kaggle https://www.kaggle.com/learn/intro-to-machine-learning
- Hands-on ML textbook (more for 'classic' machine learning - still really important to understand 'modern' models) https://www.booktopia.com.au/hands-on-machine-learning-with-scikit-learn-keras-and-tensorflow-3e-aurelien-geron/book/9781098125974.html?gad_source=1&gclid=CjwKCAiA9dGqBhAqEiwAmRpTC3W7SbJJOrI8fEi-19OxvyNLElA8Nk7iKH6nE4KDm1iLlySKgb114hoCcG8QAvD_BwE
- The paper that started it all (or at least a lot of it) https://arxiv.org/abs/1312.6199
- Adversarial Robustness Toolbox https://adversarial-robustness-toolbox.org/
- Cleverhans https://cleverhans-lab.github.io/
- Darknet diaries (please someone introduce me to Jack) https://darknetdiaries.com/
- Rob Miles https://www.youtube.com/@RobertMilesAI
- Import AI https://jack-clark.net/
- AI Daily Brief https://www.youtube.com/channel/UCKelCK4ZaO6HeEI1KQjqzWA
- Less Wrong https://www.lesswrong.com/
- Unsupervised learning https://danielmiessler.com/
- OWASP ML Top 10: https://owasp.org/www-project-machine-learning-security-top-10/
- ML Safety https://course.mlsafety.org/about
- Anatomy of an AI system: https://anatomyof.ai/

People kept asking us about the recent AI laws in California and why some were passed but one was vetoed, so we decided we'd finally better do a podcast episode on it!
Disclaimers: we're not lawyers (this will be immediately obvious) but I hope this is enlightening to other AI/tech folk. We certainly loved researching this one, and we encourage everyone who's interested to join the discussion!

In this episode we shout out Civ.ai, a non-profit we met at Berkeley when we were in the US. They create demos to show policymakers just how impactful and risky AI can be, so please do get in touch with them if you're interested! https://civai.org/

In this bonus episode we're still with Miranda and we're talking about some of the trends we're seeing around LLMs (language models) being used by adversaries to augment attacks. This could be another episode, but we have a bite sized discussion for you here!

This time we are joined by another vital member of the Mileva team, Miranda R! Unlike Tania and myself, who are data scientists who got into security, Miranda actually started as a cyber security analyst and made her way into AI. She chats about her career journey and insights on the cyber/AI intersection.

When we were in the US we rode a Waymo.. and now we chat about it here! We definitely want to chat about job displacement in another episode, but for now - here is our excuse to tax deduct the Waymo ride!

We're finally back after a bit of a break (travel is tiring). Over the last couple of weeks we attended and spoke at BSides Singapore and BSides Canberra! In this episode we cover the research discussed in our talks and the highlights of BSides in general (you know we're massive BSides fans).  

We're exhausted but we're still here! And to our knowledge we have not been hacked... in this episode we reflect on our AI and cyber security conversations from BSides Las Vegas, the AI Security Forum, DEF CON 32 and our week in the Bay Area. 

We also want to shout out these organisations:
Far Labs for hosting us: https://far.ai/labs/
CivAI, this awesome new company we met who are creating AI demos: https://far.ai/labs/
Dreadnode for their awesome LLM red teaming comp at the AI Village: https://www.dreadnode.io/
Rob Miles for his AI safety youtube channel: https://www.youtube.com/c/RobertMilesAI

Are you excited to attend hacker summer camp (BSides LV, Black Hat and/or DEF CON) in 2024? So are we!! Harriet shares some tips and tricks based on her experience last year. If you'll be in Vegas this year and see myself and Tania please say hi!

Hackertracker: https://hackertracker.app/conferences/HSCPARTIES2024/schedule/

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 in this week's digest! http://eepurl.com/i7RgRM

In this episode Tania is in New Zealand and I am in France, but that hasn't stopped us! We dive deeper into defining Artificial Intelligence Security, how it is different to AI safety and cyber security and our reflections on its past, present and future. Listen for a 0-50 on AI security.

Mileva Security Labs: https://milevalabs.com/

AI Safety Aus and NZ: https://www.facebook.com/groups/1099249420923957/

Google Trends: https://trends.google.com/trends/

Intriguing Properties of Neural Networks: https://arxiv.org/abs/1312.6199

Welcome to the first episode of the podcast. It's only up from here. Tania has been roped into presenting this with me so not only do you get to hear about us and why we care about AI security, but we also explain what it is and why YOU should care about AI security. 

Mileva Security Labs: https://milevalabs.com/

Psyber: https://psyber.com.au/

HarrietHacks: https://www.harriethacks.com/ 

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/www-project-machine-learning-security-top-10/ 

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. 

Resources:
https://academy.hackthebox.com/course/preview/introduction-to-red-teaming-ai
https://tryhackme.com/path/outline/redteaming

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 security series. Massive thanks to Microsoft for having me and Sarah Young for excellent interviewing. Check out the rest of the series, they have some really cool people on. This is also a good episode for anyone new to AI security, it covers most of the bases.

Link here: https://www.youtube.com/watch?v=sPQaJVnBSRQ&pp=ygUYaGFycmlldCBmYXJsb3cgbWljcm9zb2Z0

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/
RAISE: https://raise-project.uk/

Contact us at contact@mileva.com.au

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: http://eepurl.com/i7RgRM

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 airports but please forgive us we are not airport experts).

We refer to useful content from MITRE's resources: https://atlas.mitre.org/resources/ai-security-101

Feel free to compliment us at contact@mileva.com.au.