SS-NEWS-128: AI Cipher Unsafe, SOC Heroes, and Malware on the Blockchain!

Episode 125 October 23, 2023 00:56:38
SS-NEWS-128: AI Cipher Unsafe, SOC Heroes, and Malware on the Blockchain!
Security Serengeti
SS-NEWS-128: AI Cipher Unsafe, SOC Heroes, and Malware on the Blockchain!

Oct 23 2023 | 00:56:38

/

Show Notes

This week we discuss Malware stored on the Blockchain (coming soon to a theater near you!), how to stop Heroes in your SOC (common discussion topic amongst villains!), US Gov requesting governments stop paying ransoms, and a slightly over excited paper on using ciphers to bypass alignment restrictions in LLMs.  

I actually personally found the language issues introduced by chatting with LLMs in ciphertext more interesting personally, but...

Article 1 - The Fake Browser Update Scam Gets a Makeover

Article 2 - How to Banish Heroes from Your SOC?
Supporting Articles:
Does Your Company Lurch from Crisis to Crisis?
Delivering Security at Scale: From Artisanal to Industrial
6 ways to keep your top performers from jumping ship

Article 3 - The US wants governments to commit to not paying ransoms

Article 4 - GPT-4 IS TOO SMART TO BE SAFE: STEALTHY CHAT WITH LLMS VIA CIPHER
Supporting Articles:
Manna: Two Visions of Humanity's Future

If you found this interesting or useful, please follow us on Twitter @serengetisec and subscribe and review on your favorite podcast app!

Other Episodes

Episode 83

October 24, 2022 00:25:32
Episode Cover

SS-RPRT-083: Google Sep. 2022 Threat Horizons Report

A report!  A new report, in the torrents of blog posts and reports released by security companies! A boring report :( We discuss the...

Listen

Episode 151

October 21, 2024 00:37:07
Episode Cover

SS-NEWS-151: AI Companions Hacked

This week we discuss an attempted kidnapping and ransom of the parents of someone connected to a multi million dollar theft, stolen prompts and...

Listen

Episode 64

June 06, 2022 00:35:20
Episode Cover

SS-NEWS-064: Social Engineering Kill Chain Model!

In this episode, we discuss a Kill Chain-like model for Social Engineering attacks.  We were going to do two articles, but we went deep. ...

Listen