this post was submitted on 14 Mar 2024
3 points (100.0% liked)

Pulse of Truth

1234 readers
40 users here now

Cyber Security news and links to cyber security stories that could make you go hmmm. The content is exactly as it is consumed through RSS feeds and wont be edited (except for the occasional encoding errors).

This community is automagically fed by an instance of Dittybopper.

founded 2 years ago
MODERATORS
 

Researchers discovered multiple vulnerabilities in Google’s Gemini Large Language Model (LLM) family, including Gemini Pro and Ultra, that allow attackers to manipulate the model’s response through prompt injection. This could potentially lead to the generation of misleading information, unauthorized access to confidential data, and the execution of malicious code. The attack involved feeding the LLM […] The post Google’s Gemini AI Vulnerability let Hackers Gain Control Over Users’ Queries appeared first on Cyber Security News.

top 1 comments
sorted by: hot top controversial new old
[–] Nativeridge@aussie.zone 1 points 1 year ago* (last edited 1 year ago)

Gemini already generates misleading information, when responding by telling it information it gave was incorrect it falls back on the "Hur Dur I am just learning."

No I don't like AI