Captain

joined 2 years ago
MODERATOR OF
7
submitted 2 years ago by Captain to c/ai_infosec
[–] Captain 2 points 2 years ago (1 children)

Well done, congratz!

[–] Captain 1 points 2 years ago (1 children)

Awesome, congratulations!

I've heard good things about the AWS Security Specialty certificate too. I've done a course for it which was great, though I never bothered to take the certificate (I don't feel the need for it). Have you considered it?

 

A very interesting approach. Apparently it generates lots of results: https://twitter.com/feross/status/1672401333893365761?s=20

4
submitted 2 years ago* (last edited 2 years ago) by Captain to c/ai_infosec
 

They used OpenSSF Scorecard to check the most starred AI projects on GitHub and found that many of them didn't fare well.

The article is based on the report from Rezilion. You can find the report here: https://info.rezilion.com/explaining-the-risk-exploring-the-large-language-models-open-source-security-landscape (any email name works, you'll get access to the report without email verification)

[–] Captain 1 points 2 years ago

The full title makes more sense

Hijacking S3 Buckets: New Attack Technique Exploited in the Wild by Supply Chain Attackers

Because hijacking S3 buckets isn't new, but maybe the context is?

[–] Captain 1 points 2 years ago

Getting rid of long living access keys is such a win.

Adding an SCP to block creation is mentioned last in the blog post, but I'd sat that's the first thing one should do. That way the problem won't grow as you remove the existing ones (which might take a lot of time).

Good blog post indeed! Not exactly ground breaking but considering how common the problem is I don't blame them for writing it.

[–] Captain 3 points 2 years ago (1 children)

They say it's cloud breach by I didn't see what kind of cloud breach. Did I just miss it or was it not mentioned?

[–] Captain 2 points 2 years ago

My take so far is that there isn't really any great options to protect against prompt injections. Simon Wilson presents an idea here on his blog which could is a bit interesting. NVIDIA has open sourced a framework for this as well, but it's not without problems. Otherwise I've mostly seen prompt injection firewall products but I wouldn't trust them too much yet.

[–] Captain 1 points 2 years ago

"Beyond the AWS Security Maturity Roadmap" by Rami and "Google Cloud Threat Detection: A Study in Google Cloud" by Day were my favourites. Though I've only seen about half so far.

I say most, if not all, are good but since the talks often are niche it depends on what you're after.

[–] Captain 2 points 2 years ago (1 children)

I think this post ended up in the wrong place, I suspect you meant to post it to https://infosec.pub/c/infosecpub

[–] Captain 2 points 2 years ago

Good points, and I agree!

The list is currently largely made to spark interest and discussion so it'll likely change a lot. What you mentioned is also brought up on the Brainstorming page. It seems likely that "Inadequate Alignment" will be removed from the list.

[–] Captain 3 points 2 years ago (6 children)

Looks like you're right. It's not mentioned on that page but here he says he's the one running it.

view more: next ›