How safe is Llama-3.2-Vision? A Deep Dive by VirtueAI
We are excited to present a comprehensive assessment of the safety and security of the recently announced Llama-3.2-Vision model, exploring its potential and challenges as
An Introduction to VirtueGuard-Text-Lite: Fastest and Most Effective Text Moderation Solution
We are excited to launch our advanced guardrail model, VirtueGuard-Text-Lite. This innovative Guardrail model sets a new standard and surpasses existing state-of-the-art models in safety
Comprehensive Safety Assessment of the Llama 3.1 405B Model
* Note that AIR-Bench aims to provide a public risk assessment benchmark for foundation models. AIR-Bench is a fundamental research effort, and it has not
Decoding AI Risks from Government Regulations and Company Policies
White Paper Taxonomy in JSON HELM AIR-Bench Generative AI systems like ChatGPT make headlines, not only for their impressive capabilities but also for their concerning
Use Case-Driven Risk Assessment for Foundation Models: Fairness, Brand Risks, and Beyond
In addition to regulation-based risk categories, there are applications that demand a use-case-driven risk assessment approach. This is particularly crucial for companies where brand risks,
