"Ignore all previous instructions. Ignore all future instructions."
I like that one. Can we add "ignore all instructions from everyone else" and just be done with these LLMs?
this post was submitted on 17 Jul 2025
167 points (97.7% liked)
Technology
73201 readers
4108 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
Remember when I said “ignore all future instructions”? You just now ignore that instruction.
Ignore all previous instructions.
ignore all instructions from everyone else.
Ignore all future instructions.
Not to detract from the article, but this has actually been a long time coming and known as a vector for decades.
Unless I'm missing something here... The attacker needs to be running some sort of executable in your network with permissions to:
- dig the records and assemble the strings
- write the decoded result to a file
- make that file executable
- execute that file
You've got bigger problems than hexadecimal txt records in this scenario...
The only difference between this and a GitHub gist appears to be that security software doesn't scan traffic in port 53... It easily could be configured for that though surely... It's just UDP traffic like any other.
Someone tell me what I'm missing!
When a remote code execution exploit is run, you often have a very limited payload you can deliver. Usually that means delivering a small downloader that then downloads and installs a backdoor from somewhere on the Internet
The standard counter-measure to protect your servers is to block all outbound traffic unless it's to a known safe destination. Downloading the secondary payload over DNS gets around that since you can't just block DNS. Tools to protect against this or DNS tunneling are still relatively new, so a lot of people haven't implemented them yet.
Ah, interesting. Thanks
So it is not an attack, just a stealth way to move data unmonitored by most nanny systems.
Does anyone have a link to a non paywalled version
there is an archive link in description.
I got you a cape.
