Research
Our research program advances the science of digital evidence integrity through peer-reviewed publications, open methodology development, and cross-disciplinary collaboration between computer scientists, forensic experts, and legal scholars.
Blockchain Forensics
Advanced graph-kernel analysis for anti-money laundering detection across multi-chain environments. Our Sliced-Wasserstein distance approach provides statistically rigorous anomaly detection with published error rates meeting Daubert admissibility thresholds.
AI Admissibility Science
Establishing the scientific foundation for AI-generated evidence admissibility in legal proceedings. Research focuses on explainability requirements, error rate documentation, and the intersection of Federal Rules of Evidence with machine learning outputs.
Deepfake Detection Methodology
Development of forensically sound deepfake detection methods with quantifiable confidence intervals. Our approach combines temporal consistency analysis, generative artifact detection, and provenance verification for multimedia evidence.
Chain-of-Custody Cryptography
Novel five-layer HMAC-SHA-256 hash chain architecture for maintaining tamper-evident audit trails. Research into parallel hash verification, zero-knowledge proofs for selective disclosure, and hardware-anchored integrity guarantees.
Ghost Mode Architecture
Zero-persistence forensic processing architecture that ensures no residual data remains after evidence analysis. Research into confidential computing, secure enclaves, and memory-only computation patterns for sensitive evidence handling.
Cross-Jurisdiction Evidence Standards
Comparative analysis of evidence admissibility standards across federal, state, and international jurisdictions. Building automated compliance mapping for multi-jurisdiction case management.
Collaborate With Us
We welcome research collaborations with academic institutions, government agencies, and industry partners committed to advancing digital evidence science.
Propose a Collaboration