103

in absolutely the funniest outcome so far, you can send data to an LLM that pops a Remote Code Execution vulnerability (mastodon.social)

submitted 8 months ago* (last edited 8 months ago) by dgerard@awful.systems to c/techtakes@awful.systems

13 comments fedilink hide all child comments

courtesy @self

preprint: https://arxiv.org/pdf/2309.02926
blackhat abstract: https://www.blackhat.com/asia-24/briefings/schedule/index.html#llmshell-discovering-and-exploiting-rce-vulnerabilities-in-real-world-llm-integrated-frameworks-and-apps-37215
Tong Liu's related research: https://scholar.google.com/citations?hl=en&user=egWPi_IAAAAJ

can't wait for the crypto spammers to hit every web page with a ChatGPT prompt. AI vs Crypto: whoever loses, we win

you are viewing a single comment's thread
view the rest of the comments

[-] Soyweiser@awful.systems 8 points 8 months ago

Guess that is one way to make it mine cryptocurrency. Billions of dollars into the project, but no money to hire copyright lawyers not cybersecurity experts. Another red flag against this every being long term viable.

(Was wondering 'could you abuse a list of open LLM prompts to mine cryptocurrencies' but turns out it is worse)

this post was submitted on 25 Apr 2024

103 points (100.0% liked)

TechTakes

1490 readers

28 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 2 years ago

MODERATORS

dgerard@awful.systems