ShieldstralMistral AI
|
||||||
Related Products
|
||||||
About
Alice (formerly ActiveFence) is a security, safety, and trust platform built to protect AI systems and online platforms in the GenAI era. Powered by the world’s largest adversarial intelligence dataset, Alice safeguards over 3 billion users across more than 120 languages. Its Rabbit Hole intelligence engine continuously analyzes billions of toxic and manipulative data samples to detect emerging threats in real time. The WonderSuite platform includes tools like WonderBuild for pre-launch stress testing, WonderFence for runtime guardrails, and WonderCheck for automated red-teaming. By defending against prompt injection, jailbreaks, governance gaps, and harmful AI behavior, Alice enables enterprises and foundation model labs to innovate with confidence.
|
About
Shieldstral is a 3B open-weights, policy-adaptive multimodal safety classifier designed to evaluate text, images, and text-plus-image content using policies defined at inference time. Instead of relying on a fixed taxonomy of harm categories, it frames moderation as a binary question-answering task: users provide an instruction describing the evaluation context and strictness, a yes-or-no safety question, and the content to judge. The model reads the “yes” and “no” logits and converts them into a continuous, calibrated safety score, allowing applications to threshold or rank results by confidence rather than depend on a single discrete label. This formulation unifies prompt classification, response moderation, refusal detection, toxicity detection, and multimodal safety in one interface, while letting teams adapt policies without retraining the model. Shieldstral can evaluate prompts, responses, prompt-response pairs, images, and images with accompanying text.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Foundation model developers, enterprise AI teams, platform security leaders, and technology companies seeking advanced adversarial intelligence and AI safety solutions to secure GenAI systems and digital platforms
|
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationAlice
Founded: 2018
United States
alice.io
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Content Moderation Features
Artificial Intelligence
Audio Moderation
Brand Moderation
Comment Moderation
Customizable Filters
Image Moderation
Moderation by Humans
Reporting / Analytics
Social Media Moderation
User-Generated Content (UGC) Moderation
Video Moderation
|
||||||
|
|
|