National Cyber Warfare Foundation (NCWF) Forums


Researchers Hack AI Assistants Using ASCII Art


0 user ratings
2024-03-19 06:21:08
milo
Red Team (CNA)

 - archive -- 

Large language models (LLMs) are vulnerable to attacks, leveraging their inability to recognize prompts conveyed through ASCII art.  ASCII art is a form of visual art created using characters from the ASCII (American Standard Code for Information Interchange) character set. Recently, the following researchers from their respective universities proposed a new jailbreak attack, ArtPrompt, that […]


The post Researchers Hack AI Assistants Using ASCII Art appeared first on GBHackers on Security | #1 Globally Trusted Cyber Security News Platform.



Free Webinar : Mitigating Vulnerability & 0-day Threats


Alert Fatigue that helps no one as security teams need to triage 100s of vulnerabilities.

:



  • The problem of vulnerability fatigue today

  • Difference between CVSS-specific vulnerability vs risk-based vulnerability

  • Evaluating vulnerabilities based on the business impact/risk

  • Automation to reduce alert fatigue and enhance security posture significantly


AcuRisQ, that helps you to quantify risk accurately:




Source: gbHackers
Source Link: https://gbhackers.com/ascii-art-ai-assistant-hack/


Comments
new comment
Nobody has commented yet. Will you be the first?
 
Forum
Red Team (CNA)



Copyright 2012 through 2024 - National Cyber Warfare Foundation - All rights reserved worldwide.