Research — Lucas Espindola

Applied AI research on small, on-device models for AI agent security, and on resilient content routing for decentralized storage.

Llama-Doorman-22M

Oct 2026

An on-device prompt-injection classifier (22M parameters, ONNX int8) that tells an instruction aimed at an AI agent apart from text that merely mentions an attack. It catches 79% of attacks that rule-based checks miss at a 0.4% false-alarm rate, against 38% for the best frontier model, in about 0.24 s per check on a laptop CPU. It powers Doorman, an open-source (Apache-2.0) local app and CLI that watches what AI coding agents read and run, and holds risky steps for an engineer's approval.

Model on Hugging Face · Doorman on GitHub · How it was trained

Federated Content Routing: A Three-Tier Architecture for Resilient Content Routing in IPFS

IEEE ICC 2026

Sole author and presenter. A three-tier design for IPFS content routing: an edge query plane, a regional Byzantine-fault-tolerant control plane and a global DHT fallback, giving central-indexer latency with 99.95% availability when the edge goes down.

Paper on IEEE Xplore · Write-up

Write-ups

How we trained a small model to tell a prompt injection from a quote October 20, 2026
Llama-Doorman-22M: a 22M-param on-device classifier that catches ~2× more missed prompt injections than frontier models, and the use-vs-mention dataset, eval harness and selection rules behind it.
Federated Content Routing: A Three-Tier Architecture for Resilient Content Routing in IPFS May 27, 2026
My IEEE ICC 2026 paper: edge caches that serve quorum-signed snapshots, regional BFT clusters that only handle changes, and a global DHT that is always there. Central-indexer latency with 99.95% availability when the edge goes down.