Home/Evaluation & Observability/embedguard

embedguard

neerazz/embedguard

Cross-Layer Detection and Provenance Attestation for Adversarial Embedding Attacks in RAG Systems

GitHub

GraphCanon updated 2w · GitHub synced 2w · 25 views this month

0 stars0 forksLast push 1mo Python MIT

Decision brief

EmbedGuard, a Python-based toolkit, ensures RAG systems are fortified against adversarial embedding attacks by providing robust detection and provenance attestation mechanisms.

Good fit when

When secure communication channels and provenance tracking of data embeddings in RAG (Retrieval-Augmented Generation) systems are critical to avoid security breaches or tampering by malicious actors.
For advanced defense against specific adversarial embedding attacks, where the integration of trusted execution environments is desired for enhanced security measures.

Avoid when

If your project does not involve RAG systems or you are working with simpler data structures that do not require embedding-level security mechanisms.
EmbedGuard may not be suitable if your primary focus is on general AI model performance optimization rather than specific defense against embedding attacks in complex RAG setups.

Observed Jul 12, 2026 · Source: enrich:decision_facts

embedguard alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Active (22d since push); As of 2w
Provenance: Not a fork · Personal account; As of 2w
Security (OSV): 4 low (4 low); As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install embedguard

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

RAG_Techniques

Showcases advanced techniques for Retrieval-Augmented Generation (RAG) systems with detailed notebook tutorials.

29k★

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

4.8k★

PurpleLlama

Set of tools to assess and improve LLM security

4.3k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A toolset aimed at securing RAG systems against adversarial embedding attacks by providing detection mechanisms and provenance attestation.

Capability facts

Deploy: Self-host
Source: dockerfile:Dockerfile · Aug 1, 2026
Docker: Dockerfile present
Source: dockerfile:Dockerfile · Aug 1, 2026
CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 1, 2026
Languages: python
Source: github.language+pyproject.toml · Aug 1, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 1, 2026)

pip install -e .

Source link

README

Quick start

git clone https://github.com/neerazz/embedguard
cd embedguard
pip install -e .

---

# Install in development mode
pip install -e ".[dev]"

License

This project is licensed under the MIT License - see the LICENSE file for details.

For agents

This page has a .md twin and JSON over the API.

/tools/neerazz-embedguard.md GET /api/graphcanon/tools/neerazz-embedguard GET /api/graphcanon/graph?tool=neerazz-embedguard