Skip to content

SingGuard-NSFA

Named by 2 kept items in this workspace.

Search every workspace for SingGuard-NSFA. It matches the name as written, so it can find other things that share it.

The items that name it 2

  • [tl;dr sec] #342 - Figma's Agentic Detection, Agent Identity, Uber's Agent-(E)DR
    article2026-08-20

    Ant Group's dual-mode guardrail framework for agentic AI threats, with lightweight classification heads on frozen Qwen3.5 backbones, offering chain-of-thought reasoning for offline auditing and low-latency real-time classification, grounded in a taxonomy of 185 risk variants across 7 domains.

  • AI Security Briefing
    repo2026-07-19

    Extensible guardrail framework for agentic AI detecting operational security threats (prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, resource exhaustion) via generative reasoning and real-time classification; released as four models (0.8B, 2B, 4B,

All technologies in this workspace.