Show HN: QCMP Framework for Poison-Resistant AI Agents (ArXiv Cs.ai Pending)

1 point

6 months ago

Hey HN—after a year digging into agentic AI vulnerabilities, I've built QCMP: a 4-layer architecture to slam the door on memory poisoning. MCP's at 16K servers, but attacks like MINJA (98.2% query-only success) and AgentPoison (80%+ backdoors from 0.1% poison) expose the core flaw—memory trusts itself too much.

QCMP borrows from IIT consciousness metrics (CCI >0.90 to freeze fragments), post-quantum checksums (ML-KEM-768), CTC self-consistency (NIS >0.95), and mantis shrimp-style sparse checks (<50ms TME). OWASP/EU AI Act ready, with Rust impl tips.

PDF (in-browser view): https://github.com/bradmcevilly/qcmp-whitepaper/blob/main/QC...

First arXiv push to cs.AI—hunting endorsements (4+ recent subs). Feedback on the quantum-bio hooks or swarm layers? Open to riffs.

deepsweep.ai | linkedin.com/in/bradmcevilly

I've spent the last year tackling memory poisoning in agentic AI (e.g., 98% MINJA success via queries alone). Introducing QCMP: a 4-layer architecture blending IIT consciousness metrics (CCI >0.90 thresholds), post-quantum checksums (ML-KEM), and CTC consistency for tamper-proof agent swarms.

Key wins: Detects 0.1% AgentPoison backdoors in <50ms; OWASP/EU AI Act compliant.

PDF: https://github.com/bradmcevilly/qcmp-whitepaper/blob/main/QC...

First arXiv sub to cs.AI—seeking endorsements/feedback from the HN community. Thoughts on the quantum-bio hooks or multi-agent layers? Open to chats.

Site: deepsweep.ai | LI: linkedin.com/in/bradmcevilly