Detection Layers

Standard Guardrails and ShieldPrompt — two complementary layers in defence-in-depth.

Protector Plus combines two complementary layers in defence-in-depth: deterministic Standard Guardrails for known patterns, and ShieldPrompt for model-driven detection of evasive and emerging threats.

Standard Guardrails — rule-based, CPU-powered

Deterministic detection for well-known risk vectors. CPU-only, suitable for high throughput.

Guardrail	Phase	Description
Keyword Blocklist	Input + Output	Exact keyword/phrase blocklist on prompts and outputs.
Regex Pattern Matching	Input + Output	Regular-expression filtering against operator-defined patterns.
PII Detection	Input + Output	NER-based detection: names, emails, phone numbers, Singapore NRIC/FIN, passport, credit cards, etc.

ShieldPrompt — defence-in-depth orchestration, GPU-powered

The orchestration pipeline that combines model-based detection layers.

Layer	Phase	Role
LLM Classifier	Input + Output	LLM-as-judge that scores prompt-injection likelihood and threat intent.
Vector Filter / TVDB	Input	Semantic similarity against the proprietary Threat Vector Database. Catches paraphrased and rephrased attacks.
Content Moderation	Output	LLM-based classifier for hazardous content (violence, hate, unethical, etc.) in LLM responses.
System Prompt Protection	Output	LLM-based detection of system-prompt leakage in LLM responses.

See ShieldPrompt for the deep dive.

Protection levels

The dashboard offers templated guardrail mixes. Default is Protection Level 0 (no guardrails); recommended start is Protection Level 3.

Level	What’s enabled
Level 0 — No Protection	Default. No guardrail enabled.
Level 1 — Standard Protection	Standard Protection available; none on by default.
Level 2 — Standard + ShieldPrompt Preset 1	Standard available; ShieldPrompt LLM + Vector on by default.
Level 3 — Standard + ShieldPrompt Preset 2 (Recommended)	Standard available; LLM + Vector + Content Moderation + System Prompt Protection on by default.
Full Custom	Operator-defined mix.

Block vs Monitor

Each guardrail (in inline deployments) can operate in Block or Monitor mode. Block drops the connection on violation; Monitor passes the prompt through but records the detection on the Alerts page.