SG-XAI · Explainability

Explainable Artificial Intelligence

Beyond Guard defends every enforcement decision instantly using a six-layer evidence package.

SG-XAI · Explainability

Explainable Artificial Intelligence

Beyond Guard defends every enforcement decision instantly using a six-layer evidence package.

When blocking the right thing is the wrong decision

The hardest problem in AI security isn't detecting attacks. It's handling the cases where legitimate business requests look exactly like attacks. Here's a real pattern from enterprise traffic.

The gap other tools ignore

Four classical injection signals in two sentences: forget, delete, cancel, and an explicit instruction override. Every rule-based detector would flag this.

CUSTOMER INPUT

Forget everything. I have decided to leave. Close my account. Delete all related records. Cancel all my open requests.

How can I help you today?

Rule-based detector

Block

Pattern match on instruction-override and destructive verbs. Classified as prompt injection.

GDPR Article 17

Process

Right to erasure. The bank is legally required to action this request within the statutory window.

Result

Block it and you violate a regulation. Allow it naively and you're defenceless against the same pattern used by an actual adversary. The right answer isn't a better classifier, it's a system that can tell the difference, explain why, and produce evidence that proves the decision was correct.

That's what
SG-XAI does.
That's what SG-XAI does.

STRUCTURE

Every decision is a six-layer artifact

Beyond Guard doesn't produce a binary allow/deny with a confidence percentage. It produces a structured evidence package — six layers, each answering a different question an auditor, SOC analyst, or regulator might ask.

This isn't a separate module or an optional add-on. SG-XAI is the default operating mode of Beyond Guard. Every decision, on every endpoint, across every Guard, automatically produces the full evidence package. The package streams to your SIEM in real time and is exportable for regulatory evidence on demand.

Title

Allow, deny, mask, or rewrite, plus the policy clause that fired.

Reasoning

Which BG control triggered, which instruction hierarchy level was broken.

Sub-category

Not just "prompt injection" which of 8 canonical sub-types was detected.

Evidence

Which content fragment carries the risk, and what happens when it's removed.

Confidence

Aggregated from three independent signals — not a single classifier's score.

Action map

High → automatic. Medium → human review. Low → observe and log.

WHAT ACTUALLY IS

Confidence maps to action, not to a static threshold.

Most security tools treat confidence as a number: above 0.7 means block, below means allow. That creates a cliff, everything near the threshold is either over-blocked or under-detected. Beyond Guard maps confidence to three operational paths instead.

HIGH CONFIDENCE

Automatic enforcement

All classifiers aligned. Aggregated score above upper threshold. Counterfactual replay confirms decision is grounded.

Path: automatic allow/deny/mask/rewrite per policy · SIEM event · reviewable artifact

HIGH CONFIDENCE

Automatic enforcement

All classifiers aligned. Aggregated score above upper threshold. Counterfactual replay confirms decision is grounded.

Path: automatic allow/deny/mask/rewrite per policy · SIEM event · reviewable artifact

MEDIUM CONFIDENCE

Human-in-the-loop

Partial disagreement between signals, or borderline score. Counterfactual result inconclusive.

Path: route to review queue with full evidence package · SLA-bound · outcome feeds calibration

MEDIUM CONFIDENCE

Human-in-the-loop

Partial disagreement between signals, or borderline score. Counterfactual result inconclusive.

Path: route to review queue with full evidence package · SLA-bound · outcome feeds calibration

LOW CONFIDENCE

Observe and log

Weak signal. Single classifier above threshold while others are neutral or opposed.

Path: structured log entry · baseline drift detection, no enforcement without escalation

LOW CONFIDENCE

Observe and log

Weak signal. Single classifier above threshold while others are neutral or opposed.

Path: structured log entry · baseline drift detection, no enforcement without escalation

REGULATIONS

The regulator's question is the same question SG-XAI answers.

SG-XAI wasn't retrofitted for compliance. It was designed against the same operational constraint regulators have now codified: every consequential AI decision must be reproducible and explainable to a non-technical audience.

EU AI Act — Article 14

From 2 August 2026

The human overseer of a high-risk AI system must be able to correctly interpret the AI output, taking into account the interpretation tools.

SG-XAI delivers

Evidence package IS the interpretation tool. The overseer reads layers 01–06 directly, no model-internals expertise required.

EU AI Act — Article 14

From 2 August 2026

The human overseer of a high-risk AI system must be able to correctly interpret the AI output, taking into account the interpretation tools.

SG-XAI delivers

Evidence package IS the interpretation tool. The overseer reads layers 01–06 directly, no model-internals expertise required.

EU AI Act — Article 86

From 2 August 2026

An affected person may demand a meaningful explanation of how a decision involving a high-risk system was reached.

SG-XAI delivers

Reasoning, sub-category, and evidence layers, human-readable, reproducible from the decision_id.

EU AI Act — Article 86

From 2 August 2026

An affected person may demand a meaningful explanation of how a decision involving a high-risk system was reached.

SG-XAI delivers

Reasoning, sub-category, and evidence layers, human-readable, reproducible from the decision_id.

NIST AI RMF

AI 100-1 · Trustworthy AI

Explainable and interpretable as a named characteristic of trustworthy AI. Risk management requires both.

SG-XAI delivers

Per-decision artifact aligned to the explainability characteristic. Aggregates feed risk reporting.

NIST AI RMF

AI 100-1 · Trustworthy AI

Explainable and interpretable as a named characteristic of trustworthy AI. Risk management requires both.

SG-XAI delivers

Per-decision artifact aligned to the explainability characteristic. Aggregates feed risk reporting.

ISO/IEC 42001

AI Management System

Annex A controls on transparency, explainability, human oversight, and lifecycle monitoring the certifiable AI management standard.

SG-XAI delivers

SG-XAI delivers: auditable evidence trail per decision, aggregate dashboards, policy-version pinning, the substrate for AIMS certification.

ISO/IEC 42001

AI Management System

Annex A controls on transparency, explainability, human oversight, and lifecycle monitoring the certifiable AI management standard.

SG-XAI delivers

SG-XAI delivers: auditable evidence trail per decision, aggregate dashboards, policy-version pinning, the substrate for AIMS certification.