🚀 Medial just raised $500k in Pre-Series A. Tap to read the announcement. 🎉

Download App

Home

Switch theme

Blog . Feedback . Privacy
Community Guidelines

Back to feeds

Ayush Maurya

Stealth • 23h

What if we use AI in cybersecurity but it gets confuse and works against us ? Is that possible !!

Vishu Bheda
•

Medial • 23h

Absolutely,Hackers can trick AI systems by giving them false or confusing information. This can make the AI mistakenly see safe actions as dangerous or fail to notice real threats.

Ayush Maurya

Stealth • 22h

You mean forcing the AI to hallucinate on purpose

Vishu Bheda
•

Medial • 22h

Absolutely giving the AI false premises or information as input, causing it to build upon those inaccuracies.

Ayush Maurya

Stealth • 22h

Like wrong DB

1 replies2 likes

Replies (1)

Vishu Bheda
•

Medial • 22h

Giving AI false premises means providing incorrect info to make it generate creative outputs. It’s not the same as storing false data in a database.

0 replies

Recommendations from Medial

Darsh Singh

Stealth • 7m

W0 D3 No progress but little research, Found Gun db. Will look into it and if it fits my project or not. Any ideas upon Gun db or any suggestions are open as always!

0 replies4 likes

Sunil Huvanna

Stealth • 6m

LLM Capabilities, t2i generation via inference and resonance inside vector DB of the model is what makes images as this possible. Via : Midjourney

6 replies13 likes

Anonymous

Stealth • 7m

When you train the wrong data for the the wrong purpose

36 replies37 likes

Rahul Gupta

Stealth • 8m

If this technology (AI) goes wrong, it can go quite wrong ~ Sam Altman

11 replies14 likes

alister Rozario

Stealth • 7m

Gemini is giving wrong information. This was a question from my Btech QP, gemini was stating that the question is wrong. And chat gpt give the right answer. My sir confirmed gemini is wrong