Infosec.Pub

4,716 readers
115 users here now

To support infosec.pub, please consider donating through one of the following services:

Paypal: jerry@infosec.exchange

Ko-Fi: https://ko-fi.com/infosecexchange

Patreon: https://www.patreon.com/infosecexchange

founded 2 years ago
ADMINS
jerry
shellsharks
modbot
listing: all - local
search
1
36
Can you trust ChatGPT’s package recommendations? (vulcan.io)
 
 

From https://twitter.com/llm_sec/status/1667573374426701824

  1. People ask LLMs to write code
  2. LLMs recommend imports that don't actually exist
  3. Attackers work out what these imports' names are, and create & upload them with malicious payloads
  4. People using LLM-written code then auto-add malware themselves
2
0
Can you trust ChatGPT’s package recommendations? (vulcan.io)
 
 

“* People ask LLMs to write code

LLMs recommend imports that don't actually exist
Attackers work out what these imports' names are, and create & upload them with malicious payloads
People using LLM-written code then auto-add malware themselves”

3
4
Hijacking hallucinated package dependencies suggested by ChatGPT (vulcan.io)
submitted 2 years ago by Captain to c/ai_infosec
0 comments fedilink
view more: next ›