Guardians of the State: How We Built an Air-Gapped AI Fortress for Consumer Data
Official Schedule Context
- Date/time: 2026-06-30 · 1:55pm-2:15pm
- Track/room: AI-Native Enterprises · Leadership 1
- Speaker(s): Rachna Srivastava
- Session type/status: session · confirmed
Official Description
Every enterprise slide deck talks about "data privacy," but at the California Department of
Financial Protection and Innovation (DFPI), a single leaked Social Security Number or bank account
doesn’t just mean a bad PR day—it violates strict state consumer laws and triggers massive
regulatory security breaches. When your raw data includes petabytes of unredacted fraud complaints,
dark web scam networks, and banking statements, standard commercial public APIs are an absolute non-
starter. This talk breaks down the exact enterprise architecture the DFPI uses to leverage frontier-
level reasoning on highly sensitive data without crossing legal lines. We will walk through the code
and infrastructure of our sovereign data pipeline. Attendees will learn: The Infrastructure: How we
host and serve local, open-weights models (like Llama 3 or Mistral) in a strictly air-gapped, secure
cloud environment. The Sanitization Stack: How we built a multi-stage PII scrubbing pipeline that
uses high-speed deterministic regex combined with a small, specialized local LLM to handle messy,
unstructured text. The Validation Loop: How we technically validate that zero sensitive data leaks
into model context weights or logging files. No promissory corporate hoopla here—just real, hard-
earned architecture patterns and code snippets from a state regulator showing how to ship secure,
local AI. Key Takeaways for the Audience: Learn to build a dual-pass PII sanitization pipeline for
unstructured financial data. Understand the resource and latency trade-offs of running air-gapped,
open-weight models locally vs. commercial APIs. Discover how to set up automated validation
frameworks to detect and stop context poisoning or logging leaks.
Related YouTube Video
Cognitive Shield Real Time Real Smart - Rachna Srivastava (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.
Supporting Slides
- youtube 5_QWh4LGoxg slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube 5_QWh4LGoxg dense slides (18 viable slide images).
- Related slide/OCR pages:
- youtube 5_QWh4LGoxg dense slides
- youtube 5_QWh4LGoxg reconstructed slides
- youtube 5_QWh4LGoxg slides
- Slide-derived terms:
fraud,management,detection,flow,payment,graph,chat,user,case,examination,profile,portal,lost,knowledge,level,distribution,processing,search