The developer of WormGPT is selling access to the chatbot, which can help hackers create malware and phishing attacks, according to email security provider SlashNext.
WormGPT Is a ChatGPT Alternative With ‘No Ethical Boundaries or Limitations’::undefined
A scary possibility with AI malware would be a virus that monitors the internet for news articles about itself and modifies its code based on that. Instead of needing to contact a command and control server for the malware author to change its behavior, each agent could independently and automatically change its strategy to evade security researchers.
The limiting factor is pre existing information. It’s great at retrieving obscure information and even remixing it, but it can’t really imagine totally new things. Plus white hats would also have LLMs to find vulnerabilities. I think it’s easier to detect vulnerabilities based on known existing techniques than it is to invent totally new techniques.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@lemmy.world
This is a most excellent place for technology news and articles.
English
A scary possibility with AI malware would be a virus that monitors the internet for news articles about itself and modifies its code based on that. Instead of needing to contact a command and control server for the malware author to change its behavior, each agent could independently and automatically change its strategy to evade security researchers.
to quote something I just saw earlier:
I was having a good day, we were all having a good day…
now… no sleep. thanks
If it helps you sleep, that means we could also publish fake articles that makes it rewrite its own code to produce bugs/failures
The limiting factor is pre existing information. It’s great at retrieving obscure information and even remixing it, but it can’t really imagine totally new things. Plus white hats would also have LLMs to find vulnerabilities. I think it’s easier to detect vulnerabilities based on known existing techniques than it is to invent totally new techniques.