HCISS R&D builds explainable AI security, blockchain trust and post-quantum governance for critical infrastructure, from EV charging networks and industrial control systems to urban air mobility.
A composable AI cybersecurity framework for critical infrastructure. Machine-learning "gene families" are validated for compatibility before they are combined, producing calibrated, auditable threat detection for EVSE and ICS environments, with post-quantum cryptographic governance built in.
Secure, blockchain-backed management of urban air mobility fleets. UAV authentication, verified service data, and an Autonomous Breach Protection Dashboard for hazard and threat analysis across every stage of flight.
Alerts with statistically valid confidence bounds operators can act on.
Lattice-based signing of training data, models and audit records.
Oracle-verified data and immutable audit trails through BSECALink.
OCPP, SCADA and topology-aware detection for energy infrastructure.
Our R&D is built on documented theory and developed with academic and laboratory partners.
CDMLT technical specification co-authored with university researchers, targeting arXiv publication.
CDMLT developed in active engagement with Argonne's EVSE security research program.
Scientific advisory leadership from the Centre's Data/AI Research Team.
CDMLT's gene composition framework builds on Alshammari et al., ICLR 2025.
Both are research programs. CDMLT is in active development and HCISS is seeking pilot partners in EVSE and ICS environments. UAM Fleet Management is a research and case-study initiative.
Research findings feed our AI-SAMA architecture and services, particularly calibrated detection, explainable AI decisions and post-quantum integrity for audit records.
Yes. HCISS works with research programs, critical infrastructure operators and federal agencies. Contact us with your environment and goals.
Deploying or securing EV charging, industrial control systems or AI-powered security tools? Let's talk about piloting our research in your environment.