Welcome to our

Cyber Security News Aggregator

Cyber Tzar

provide a

cyber security risk management

platform; including automated penetration tests and risk assesments culminating in a "cyber risk score" out of 1,000, just like a credit score.

First slide label

Some representative placeholder content for the first slide.

Second slide label

Some representative placeholder content for the second slide.

Third slide label

Some representative placeholder content for the third slide.

Jailbreaking LLMs with ASCII Art

published on 2024-03-12 11:12:15 UTC by Bruce Schneier
Content:

Researchers have demonstrated that putting words in ASCII art can cause LLMs—GPT-3.5, GPT-4, Gemini, Claude, and Llama2—to ignore their safety instructions.

Research paper.

Article: Jailbreaking LLMs with ASCII Art - published 2 months ago.

https://www.schneier.com/blog/archives/2024/03/jailbreaking-llms-with-ascii-art.html
Published: 2024 03 12 11:12:15
Received: 2024 03 12 11:24:41
Feed: Schneier on Security
Source: Schneier on Security
Category: Cyber Security
Topic: Cyber Security
Views: 0