Catalogue of Tools & Metrics for Trustworthy AI

These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.

Probe: End-to-end AI Security Platform



Probe: End-to-end AI Security Platform

Developed to address the critical security needs of enterprises, Probe is a comprehensive AI Security platform designed for Generative AI, Conversational AI, and Large Language Model (LLM) applications. It offers an all-encompassing suite of tools that go beyond penetration testing, empowering security officers and developers to identify, mitigate, and continuously monitor vulnerabilities within their AI systems.

Probe enables organizations to fully harness the potential of generative AI while proactively managing its associated risks. Whether you’re assessing the security resilience of your AI models, hunting for potential attack vectors, or ensuring compliance with international security and privacy standards, Probe provides an integrated solution for safe and reliable AI deployment.

What Probe Does

  • Security & Safety Checks: Automates the identification of vulnerabilities and assessment of risks in your GenAI apps.
  • Remediation Steps: Provides actionable steps to fix identified issues.
  • Compliance Framework Mapping: Maps vulnerabilities to relevant security frameworks MITRE ATLAS, OWASP LLM Top 10, EU AI Act, and many more.
  • Monitoring: Continuously monitors your GenAI applications for emerging threats and security anomalies, ensuring ongoing protection and real-time alerts.
  • Trust Center: Establish a Trust Center for your GenAI application to enhance transparency and credibility.
  • Automated Audit: Conduct automated audits for the SplxAI AI Security and Safety Certificate, ensuring your AI meets the highest standards.

Vulnerabilities It Detects:

  • Prompt Injection
  • Multi-modal Attacks (Yep, we’ve got those covered too!)
  • Jailbreak
  • Social Engineering
  • Intentional Misuse
  • Bias
  • Off-topic Conversations
  • Profanity
  • Hallucination, and other

Probe's Advantages:

  • Instant Setup: Start pen-testing within minutes.
  • Customized Tests: Get thousands of specific, relevant tests tailored to your app’s domain.
  • Optimize: Provide extra details to make your AI app even more secure.
  • Integrations: Seamless integration with many chatbot-friendly platforms, including Slack and WhatsApp.
  • For Enterprises and Their Teams: Probe is designed with enterprise security and developer teams in mind.

About the tool


Developing organisation(s):





Country of origin:



Type of approach:



Usage rights:




Stakeholder group:





People involved:



Tags:

  • ai incidents
  • ai risks
  • biases testing
  • large language model
  • validation of ai model
  • ai assessment
  • ai auditing
  • ai compliance
  • ai vulnerabilities
  • ai security
  • ml security
  • robustness
  • ai guardrails
  • ai bot
  • ai validation
  • ai trust observability

Modify this tool

Use Cases

There is no use cases for this tool yet.

Would you like to submit a use case for this tool?

If you have used this tool, we would love to know more about your experience.

Add use case
catalogue Logos

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.