Papers and resources related to the security and privacy of LLMs 🤖
-
Updated
Jun 8, 2025 - Python
#
llm-privacy
Here are 11 public repositories matching this topic...
[NeurIPS D&B '25] The one-stop repository for LLM unlearning
open-source benchmarks right-to-be-forgotten privacy-protection unlearning membership-inference-attacks membership-inference llms llm-privacy llm-unlearning llm-evaluation-metrics
-
Updated
Mar 18, 2026 - Python
The fastest Trust Layer for AI Agents
security ai-agents ai-agent llm-security ai-runtime llm-privacy prompt-security llm-guard llm-guardrails agentic-ai cx-agent
-
Updated
Feb 3, 2026 - Python
An Execution Isolation Architecture for LLM-Based Agentic Systems
ai sandbox gpt isolation multi-agent-systems ai-agents openai-api llm chatgpt langchain genai llm-agent llm-security llm-framework llm-privacy llm-platform llm-based-systems genai-security
-
Updated
Jan 31, 2025 - Python
Make Zettelkasten-style note-taking the foundation of interactions with Large Language Models (LLMs).
knowledge-graph obsidian graph-based zettlekasten second-brain obsidian-md large-language-models llm ollama llm-privacy docling obsidian-assist
-
Updated
May 19, 2025 - Python
Semantic PII Masking & Anonymization for LLMs (RAG). GDPR-compliant, reversible, and context-aware. Supports LangChain & OpenAI
nlp anonymization masking data-anonymization user-data rag ai-privacy model-data ai-tool llm-privacy ai-application model-tools rag-data
-
Updated
Jan 18, 2026 - Python
🔒 Detect security leaks in AI-assisted codebases. Static analysis tool for Python & JS/TS with cross-file taint tracking.
-
Updated
Dec 29, 2025 - Python
Example of running last_layer with FastAPI on vercel
-
Updated
Apr 5, 2024 - Python
Local-first safety/control harness for AI coding agents with reviewable handoff packets, route audits, and bounded cloud escalation.
developer-tools model-evaluation ai-safety human-in-the-loop data-governance privacy-first local-first qwen llm-privacy agent-orchestration fail-closed
-
Updated
Aug 2, 2026 - Python
Local proxy for Claude Code that redacts sensitive data (names, emails, IDs, keys) before it leaves your machine and restores it in the reply
python privacy proxy claude cli-tool pii-detection data-redaction ai-tools anthropic llm-privacy gliner claude-code
-
Updated
Aug 1, 2026 - Python
🛡️ Scrimward — local, fail-closed redaction proxy for AI coding tools (Claude Code · Codex · Cursor · Copilot · Gemini …): mask secrets, PII & images on your machine before they reach the cloud. (Early development.)
macos redaction security privacy proxy openai codex cline pii data-loss-prevention aider anthropic llm-privacy ai-coding claude-code
-
Updated
Jul 10, 2026 - Python
Improve this page
Add a description, image, and links to the llm-privacy topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-privacy topic, visit your repo's landing page and select "manage topics."