DSP-inspired multirate wrappers for GPT with adaptive hyperparameters and faster training.

Autonomous Red Team: Multi-Agent Adversarial Security Testing — paper + proof-of-concept framework | DAI-2513 | Dissensus AI Working Paper

ASRI: Aggregated Systemic Risk Index for Cryptocurrency Markets — paper + real-time monitoring system | DAI-2509 | Dissensus AI Working Paper

Minimal Tensor Logic AI engine in PyTorch – Datalog reasoning as tensor operations (einsum) and neural networks in one framework.

Adversarial robustness evaluation framework for ML-based NIDS. Categorical robustness framework, the False Champion Problem. Backs IEEE Access submission. DoD-funded research with West Point.

Central index for my research projects, code, publications, and Zenodo‑archived materials, including work on spaceborne lidar, urban forestry, vegetation modeling, and open-source geospatial workflows.

Constraint-enforcing synthetic IoT packet generation. Two methods: statistical learning (PCA + dual OCSVM/IF gating, ~1,091 pkts/sec) and a genetic algorithm (composite fitness, ~5.7 pkts/sec, 0.62% anomaly). Amplifies the 5-sample ARP Spoofing class by 200x. All 12 ACI-IoT-2023 categories pass independent validators. ICCCN 2026 submission.

Hybrid LSTM-Markov attack chain forecasting for MITRE ATT&CK. Learns from 4,849 campaign chains + 8,437 real intrusion traces. Generates 26,051 risk-ranked multi-step attack futures via constrained beam search. 86% next-step accuracy, 0.76 Pearson correlation with NCISS severity. SECRYPT 2026 submission.

Official implementation of the Lattice Stabilization Protocol for AGI Alignment (Type-IV). Implements zero-knowledge tensor bridging for hyper-dimensional manifolds.

ANIT — Narrative Architecture of Textual Invariance: computational verification scripts and materials for a structural narrative model based on textual invariance. / ARQUITETURA NARRATIVA DE INVARIÂNCIA TEXTUAL (ANIT) Um Modelo Estrutural de Reorganização Narrativa com Preservação Integral da Materialidade Textual

Multimodal LLM hallucination quantification via KL-smoothed scores + spectral/energy models (RKHS, hypergraphs).

AI testbed for mission-critical software optimization using telemetry, ML, and Bayesian tuning (SmallSat 2025)

Orchestrate multi-agent AI tasks in TypeScript, delegate work across models, and run on Telegram, WhatsApp, Discord, iMessage, CLI, and MCP

Code and experimental setup for investigating how exposure to social-media-style language affects the behavior of large language models, focusing on toxicity, sentiment, and coherence.

2.5 CNN: leverage 2D CNNs to pretrain 3D models for low-data COVID-19 CT diagnosis. Official code for Electronics (MDPI) 2025, 14(13):2571.

EEG subject identification project @ HERO Lab!!

Official DoLQ implementation: multi-agent LLM framework for discovering physically plausible ODEs from observational data.

Research-oriented implementation of SVM-X for tabular local explanations.

Analysis code for: Associations Between Physical Activity Intensity and Experience, Self-Regulation, and Self-Reported Interoceptive Accuracy and Attention

Scripts to interpret Mixture-of-Experts (MoE) language models at the expert level