Harriet Farlow

Harriet Farlow is the CEO of AI Security company Mileva Security Labs, a PhD Candidate in Machine Learning Security, and creative mind behind the YouTube channel HarrietHacks. She missed the boat on computer hacking so now she hacks AI and Machine Learning models instead. Her career has spanned consulting, academia, a start-up and Government, but don’t judge her for that one. She also has a Bachelor in Physics and a Master in Cyber Security. She calls Australia home but has lived in the UK and the US. Her ultimate hack was in founding her own AI Security company but if Skynet takes over she will deny everything and pretend the AI stood for Artificial Insemination, like her Mum thinks it does. (Sorry Mum but I’m not really a Medical Doctor).

Chantelle Ralevska is the Founder and CEO of Psyber, a startup delivering cybersecurity consulting services and security awareness training to businesses and schools across Australia. Chantelle has delivered cybersecurity training to over 440,000 employees globally, and has worked in Security at Macquarie Group, Westpac and Woolworths, to name a few. Chantelle is currently a Cybersecurity Masters student at UNSW and an avid YouTube content creator, where she captivates and educates over 500K viewers about cybersecurity, careers, university and more!


Session

09-28
14:30
55min
On Your Ocean's 11 Team, We’re the AI Guys (Technically Girls)
Harriet Farlow, Chantelle Ralevska

One of the best parts of hacker summer camp is the glitz and glam of the Vegas Strip. Many have explored hacking casinos (on and off stage). Unfortunately, it’s not like it is portrayed in the Ocean’s franchise… In real life there’s much less action, no George Clooney, and it’s a lot harder to pull off a heist than it seems.

Or is it? Well, fortunately we’re not your typical hackers and this isn’t an Ocean’s movie. We’re AI and Cyber experts, and we use the latest hacking and adversarial machine learning techniques to socially engineer our target, and then disrupt, deceive and disclose information from Artificial Intelligence systems.

We chose our target very carefully: Canberra Casino. It’s the best casino in our city… it’s also the only casino but that’s not the point.

The casino industry is at an interesting inflection point. Many large casinos have already adopted AI for surveillance and gameplay monitoring, smaller casinos are starting to make the transition, and there’s only a couple of companies in the world that provide this software. It’s ripe for exploitation.

In this talk, we are going to show you how we socially engineer our target, bypass casino AI systems - facial recognition, surveillance systems and game monitoring - and deepfake our way out of trouble.

AI Security is the new cyber security threat, and attacks on AI systems could have broad implications including misdiagnoses in medical imaging, navigation errors in autonomous vehicles… oh, and successful casino heists.

This talk was last delivered at DEF CON in Las Vegas, so we come with many lessons learnt straight from the source (and may or may not be on a few watch lists).

Main Track
Main Track