Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
SingProbe Technical Report
Sing Team
Runtime guardrails are essential for reliable large language model (LLM) deployment, yet existing approaches typically rely on independent, external models that introduce additiona…
cs.CR2026
SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
SingGuard Team
We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code…