Lucene search
K
Catalog
Vendors
Products
Timeline
Vulnerabilities
Sources
Documentation
Blog
Glossary
FAQ
Brand assets
Assessment
Agents dashboard
Agent Scanning
API Scanning
Assessment API
Alerts
Email notifications
Webhook notifications
Alerts API
SBOM package analysis
API Reference
Support
Settings
Sign in

AI jailbreaks: What they are and how they can be mitigated

🗓️ 04 Jun 2024 17:00:00Reported by Microsoft Threat IntelligenceType 
mssecure
 mssecure🔗 www.microsoft.com👁 13 Views

AI jailbreaks and how to mitigate them in generative AI systems. Understanding AI jailbreak, attack techniques and Microsoft's approach to AI red teaming. Generative AI susceptibility and characteristics likened to inexperienced employees

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

Book a live demo
04 Jun 2024 17:00Current
7.4High risk
Vulners AI Score7.4
ai jailbreakmitigationsharmtechniquesmicrosoft ai red teamingprompt injectionevasionmodel manipulationai safety ontologyai assistantcrescendo attackgenerative ai susceptibilityai characteristicsguardrailsresponsible ai approach
13