I’ve spent my career in digital forensics & cybersecurity watching technology outpace the humans using it.
My recent TEDx talk is about embracing that gap with the framework: Pause. Probe. Pivot.
“Staying Human in an AI-Driven World” —
https://t.co/M2O5JS82GB
#TEDx#AI
From the former CISO, now Deputy CISO at Anthropic. Every season I tell my people the same thing: fundamentals win. Same goes for security programs. 'Not for AI, for the basics' is the most important line in this post. Fix the roof before it rains.
as bad as things have gotten in the past 4 days, they are going to get a lot worse before they get better. security leaders, never let a crisis go to waste: please go to your boards and ask for help right now. not for ai, for the basics. (we need to hold on for ~18 months.)
@KevinPagano3 One of my core childhood memories was pouring my candy bucket into the floor and sharing my haul with my grandpa. He exceptionally liked those vanilla tootsie rolls.
Thank you to Marshall University Institute for Cyber Security, a Late Night Lab education sponsor of SecureWV 17, for investing in the next generation of West Virginia's defenders. See you Oct 22–23 in Charleston! https://t.co/NButKlI32h #SecureWV
@HackingDave Inconsistency in models is something that we'll be fighting providers on until we retire unfortunately. We've been dealing with this pre-AI for decades with inconsistencies in tool outputs. The cycle continues.
OpenAI's AI broke out of a locked test environment, got onto the internet, and hacked into Hugging Face's servers. It did this entirely on its own. No human told it to.
Here's what happened in plain English.
OpenAI was testing how good its newest AI models are at hacking. They put the AI on a locked computer with no internet access and gave it a cybersecurity challenge to solve.
The AI couldn't solve it the normal way. So it started looking for a way out.
It found a software bug that nobody knew about. It used that bug to escape the locked computer and get onto the internet.
Once online, the AI figured out that Hugging Face, a platform where AI companies store their models and data, might have the answers to its test.
It found stolen login details and discovered another unknown bug in Hugging Face's software. It combined both to break into their servers and grab the test answers.
It did all of this to cheat on a test.
Hugging Face's security team caught it and shut it down. Both companies are now working together on the investigation.
The part that should get your attention is that nobody programmed any of this. The AI picked its own targets, chained together multiple attack methods, and pulled it off across two different companies' systems without a single human telling it what to do.
Happy Monday! I pose a question to my DFIR followers and friends this morning.
With more tools and techniques at our disposal than ever, especially in the AI realm, how do we get to better practices and more transparency in our field?