ml-security

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

Policy-as-Code guardrails for ML and LLM systems: OPA/Kyverno policies, compliance mappings, signed bundles, evidence trails, and plugin index.

Robust adversarial training framework for deep learning malware classifiers. Implements continuous embedding-layer perturbations (FGSM/PGD) on a decoupled MalConv architecture to mitigate feature-space evasion attacks. Evaluates model resilience, latent distribution shifts, and cybersecurity robustness. Designed for ML Security research.

Model extraction attack toolkit that reconstructs black-box models through API queries.

Exposure intelligence for the AI-infrastructure layer — finds and weighs leaked credentials, MCP/agent configs, git-metadata secrets, and supply-chain risk, and tells you which exposures to trust. Active verification, orphan-signal triage, SARIF dedup. OWASP LLM + MITRE ATLAS tagged.

Security scanner for ComfyUI custom nodes and node-based workflow plugins. Static analysis pipeline + ML, OSS Apache 2.0.

Cryptographic gates, capability delegations, lockboxes, and vector isolation primitives

MLSec Application Security Testing Guide (MLASTG) — Enterprise & Defense-Grade Security Verification and Testing Standard for Machine Learning and LLM Systems

Educational research demonstrating weight manipulation attacks in SafeTensors models. Proves format validation alone is insufficient for AI model security.

Minimal reproducible PoC of 3 ML attacks (adversarial, extraction, membership inference) on a credit scoring model. Includes pipeline, visualizations, and defenses

A learning-focused simulation of adversarial attacks against ML-based network intrusion detection systems within a Zero-Trust architecture, including constrained adversarial modeling, policy enforcement, and security-focused evaluation metrics.

Static pre-production security scanner for AI systems, covering models, datasets, RAG, prompts, agent tools, MCP, and AI supply-chain risk.

Collection of Python security analysis tools for ML models and infrastructure. Includes FGSM harness, model inspection, poison monitoring, and deployment security validation.

CLTEcho is an advanced HTTP Request Smuggling detection suite featuring AI-powered analysis, concurrent scanning, and comprehensive reporting. With 6 threat detection types, ML-based anomaly detection, HTTP/2 support, and WAF bypass techniques, it delivers enterprise-grade security testing with professional HTML/JSON reports for security researcher

Open-source ML network-flow detector that turns CICFlowMeter traffic into deterministic analyst-facing security incidents. CLI + Docker.

GitHub Actions CI/CD pipeline for automated AI red teaming with Palo Alto Networks Prisma AIRS

Static scanner that detects code-execution backdoors in PyTorch/pickle ML model files (pickle-deserialization RCE), with an offensive demo generator. Python, stdlib-only.

security foundations to a defended capstone: threat modeling, web security, malware analysis, network defense, cryptography, ML-driven security analytics, cloud & privacy - culminating in a team defensive architecture

Control a 5-DOF Lynxmotion robotic arm using a vision language model for object detection and task planning

This is a software framework that can be used for the evaluation of the robustness of Malware Detection methods with respect to adversarial attacks.