Ant Group unveils AI safety models for agents and multimodal systems

2026-07-13T09:31:31Z

Ant Group unveils AI safety models for agents and multimodal systems

Ant Group unveils AI safety models for agents and multimodal systems

2026-07-13T09:31:31Z

Latest news and trends about tech in China

Share this:

Ant Group’s AI Safety Lab has open-sourced SingGuard-NSFA, a safety guardrail model for autonomous agents, and disclosed details of SingGuard, a multimodal safety model. SingGuard-NSFA is designed to detect risks such as prompt injection, sensitive data theft, malicious code execution, resource abuse, and permission misuse before agents take action.

The model covers seven major risk categories, 28 subcategories, 185 scenarios, and 133 languages, with nearly 100,000 samples in its evaluation system. Ant said the model is available in 0.8B, 2B, 4B, and 9B versions and can make a single risk judgment in about 50 milliseconds. [

Latest stories

Popular articles

DJI launches first VTOL fixed-wing cargo drone EV50, says it set Everest altitude record

Google reportedly beats Apple to TSMC's 2nm chip debut with Tensor G6

Insta360 unveils vision for AI-powered Cameraman robot on 11th anniversary

UBTECH says full-size humanoid robots typically run for only two to four hours amid U1 battery criticism

ByteDance's Doubao and Alibaba's Qwen to shut down AI agent features on July 15

BYD debuts first luxury off-road SUV under its Yangwang marque

TechNode Group

沪ICP备14046707号-4