secure-ai

Star

Here are 18 public repositories matching this topic...

Language: All

Filter by language

All 18 Python 9 Shell 2 HTML 1 Svelte 1

Sort: Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

EzgiKorkmaz / adversarial-reinforcement-learning

Star 127

Reading list for adversarial perspective and robustness in deep reinforcement learning.

deep-reinforcement-learning ai-safety machine-learning-security ai-security robust-machine-learning ai-alignment safe-reinforcement-learning robust-reinforcement-learning responsible-ai adversarial-reinforcement-learning secure-ai ml-security llm-security reinforcement-learning-safety llm-safety artificial-intelligence-security artificial-intelligence-alignment robust-deep-reinforcement-learning reinforcement-learning-security large-language-model-safety

Updated Jul 25, 2025

AuraFriday / mcp-link

Star 14

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

chrome-extension safari-extension mcp sse firefox-extension browser-extension semantic-search docker-sandbox secure-ai ai-agent sse-server ai-automation ai-integration agent-tools model-context-protocol mcp-server ai-toolbox ai-plugins mcp-store ai-commerce

Updated Sep 29, 2025
HTML

This project integrates Hyperledger Fabric with machine learning to enhance transparency and trust in data-driven workflows. It outlines a blockchain-based strategy for data traceability, model auditability, and secure ML deployment across consortium networks.

machine-learning smart-contracts blockchain traceability consortium data-integrity hyperledger-fabric-network decentralized-machine-learning secure-ai ledger-based fabric-chaincode-go ml-lifecycle ai-governance auditability

Updated May 29, 2025
Shell

nshkrdotcom / ASKA

Sponsor

Star 7

Secure Computing in the AI age

security cryptography privacy encryption ai artificial-intelligence cybersecurity tee data-protection hardware-security trusted-execution privacy-preserving trusted-computing secure-enclave ai-security secure-computing secure-ai confidential-computing ai-infrastructure nshkr-security

Updated May 22, 2025

OleGustavDahlJohnsen / project-agora

Star 4

Project Agora: MVP of the Concordia framework. An ethical, symbiotic AI designed to foster and protect human flourishing.

sensor-fusion ethical-artificial-intelligence ai-ethics edge-ai on-device-ml secure-ai multimodal-perception ai-governance distributed-ai apple-intelligence real-time-inference context-aware-ai human-ai-symbiosis symbiotic-ai sensormesh trust-horizon casual-traceability sanctum-protocol shofar2 orchid-protocol

Updated Aug 10, 2025
Python

Balchandar / intentusnet

Star 4

IntentusNet - Deterministic intent routing runtime for agent execution, with explicit fallback, transport abstraction, and clear operational boundaries.

ai mcp protocol multi-agent routing-engine multi-agent-systems ai-agents intent-based secure-ai ai-tools distributed-ai mcp-adapter agent-runtime deterministic-routing intent-routing fallback-routing

Updated Dec 27, 2025
Python

awesome-ai-agents-security

ProjectRecon / awesome-ai-agents-security

Star 3

A living map of the AI agent security ecosystem.

awesome jailbreak static-analysis cybersecurity sandboxing awesome-list vulnerability-scanners autonomous-agents ai-agents red-teaming ai-security guardrails runtime-protection secure-ai large-language-models llm generative-ai prompt-injection llm-security llm-ops

Updated Dec 10, 2025

CoderGuy009 / MediSight.AI

Star 2

💻🔒 A local-first full-stack app to analyze medical PDFs with an AI model (Apollo2-2B), ensuring privacy & patient-friendly insights — no external APIs or cloud involved.

transformers pytorch tailwindcss privacy-first pdf-analyzer fastapi chat-interface healthtech secure-ai fullstack-app llm ai-healthcare local-llm medical-report-analysis apollo2-2b

Updated Apr 21, 2025
Python

natharmatron / MediSight.AI

Star 2

💻🔒 A local-first full-stack app to analyze medical PDFs with an AI model (Apollo2-2B), ensuring privacy & patient-friendly insights — no external APIs or cloud involved.

transformers pytorch privacy-first pdf-analyzer fastapi chat-interface healthtech secure-ai fullstack-app llm ai-healthcare local-llm medical-report-analysis apollo2-2b

Updated Dec 30, 2025
Python

popivanova / airlock

Star 1

airlock is a cryptographic handshake protocol for verifying AI model identity at runtime. It enables real-time attestation of model provenance, environment integrity, and agent authenticity - without relying on vendor trust or static manifests.

threat-modeling autonomous-agents zero-trust audit-trail ai-security secure-ai protocol-design trust-infrastructure ai-identity open-specification ai-identity-management agent-verification federated-trust cryptographic-handshake runtime-attestation registry-governance verification-protocols stream-verification block-verification enclave-attestation

Updated Nov 28, 2025

scthornton / secure-chatbot-panw-openai

Star 1

Secure Python Chatbot with PANW AIRS protection and OpenAI API

python chatbot openai secure-ai openai-api chatgpt prisma-airs

Updated Oct 27, 2025
Python

didinj / fastapi-secure-ai-langchain-hugging-face-transformers

Star 1

Build a Secure AI App with FastAPI, LangChain, and Hugging Face Transformers

python ai fastapi secure-ai hugging-face-transformers langchain

Updated Jul 3, 2025
Python

Balchandar / emcl-protocol

Star 1

A zero-trust encrypted transport layer for AI agents and tools, with AES-GCM encryption, HMAC signing, and identity-aware JSON-RPC messaging.

jwt protocol json-rpc aes-gcm hmac zero-trust ai-security secure-ai agent-framework encrypted-communication agent-security secure-transport emcl encrypted-model-context-layer

Updated Dec 3, 2025
Python

scthornton / secure-chatbot-panw-claude

Star 1

Secure Python Chatbot with PANW AIRS protection and Claude API

python chatbot claude secure-ai claude-api

Updated Oct 27, 2025
Python

MasterCaleb254 / maais-runtime

Star 1

A security runtime that sits inside AI agents to block unauthorized actions, enforce accountability, and prevent misuse in real time

ai-security runtime-security policy-enforcement defense-in-depth secure-ai mitre-atlas ai-governance llm-agents agentic-ai langraph

Updated Dec 26, 2025
Python

ind4skylivey / livey-secure-ai-workflow

Star 0

🛰️ Livey Secure AI Workflow – LLM-agnostic security & code review for serious devs. Cloud or local, your choice.

cli workflow code-review security-automation devsecops ai-security secure-ai prompt-engineering llm-security

Updated Dec 5, 2025
Shell

Falk33n / chat-ollama

Star 0

A self-hosted AI chatbot for privacy-conscious users. Runs locally with Ollama, ensuring data never leaves your device. Built with SvelteKit for performance and flexibility. No external dependencies—your AI, your rules. 🚀