From the 1 of 2 linked papers with an AI index.
2 papers
cs.CR2026
SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
SingGuard Team
The paper introduces SingGuard-NSFA, a framework that adds guardrails to agentic AI systems to detect and block operational threats like prompt injection and malicious code request…
cs.CV2026
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
SingGuard Team
Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can ar…