Tier-0 Data Loss Prevention

Stop Data Leaks At The Edge.

If you're using a cloud proxy to scan for PII, you've already exposed the data. AiRysk performs Named Entity Recognition (NER) locally on the Windows endpoint—ensuring cleartext payload never leaves the device.

Alarms
17 total
All (17)Open (16)Acknowledged (0)Resolved (1)
HighOpen AI

PII data shared with AIchatgpt.com

Rule triggered. Risk score: 68%. Categories: pii, internal. Findings: 12.

device:KT-STORMTROOPER
host:chatgpt.com
HighOpen AI

Company secrets sharedchatgpt.com

Rule triggered. Risk score: 68%. Categories: pii, internal. Findings: 12.

device:KT-STORMTROOPER
host:chatgpt.com
HighOpen AI

PII data shared with AIgrok.com

Rule triggered. Risk score: 79%. Categories: pii, internal. Findings: 12.

device:KT-STORMTROOPER
host:grok.com

Live Dashboard Replica: Security Alarms & Redaction Tokens

Intelligent, Context-Aware DLP

Legacy regex rules flag endless false positives. AiRysk correlates multiple analysis tiers to determine actual business risk.

Local GLiNER ONNX Models

The AiRysk Windows Agent (`ContentIntelligenceEngine.cs`) runs an optimized GLiNER ONNX model locally. It swaps Social Security Numbers, Credit Cards, and specific IPs with secure placeholders (like [IP_REDACTED]) *before* forwarding telemetry to the EKS cloud.

AWS Bedrock Correlation

Once the securely redacted prompt hits the cloud, AiRysk routes it via a private VPC Interface Endpoint to Amazon Bedrock (Claude 3.5 Sonnet). The model evaluates the context of the conversation (e.g., "Is this proprietary source code, or generic boiler plate?") to calculate a definitive Risk Score.

Tenant Memory & RAG

Connect your organization's documentation to the `TenantMemory` core. AiRysk performs RAG (Retrieval-Augmented Generation) against your specific company projects and code names to ensure the DLP engine strictly flags your unique intellectual property.

Zero Cloud Retention

By enforcing Redaction at the Edge, the AiRysk Cloud never receives, processes, or stores cleartext PII. Your conversational payload remains completely secure, negating the risk of a supply-chain cloud breach.