llm-guard
LM protection framework
A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities.
The Security Toolkit for LLM Interactions
1k stars
19 watching
157 forks
Language: Python
last commit: about 1 month ago
Linked from 1 awesome list
adversarial-machine-learningchatgptlarge-language-modelsllmllm-securityllmopsprompt-engineeringprompt-injectionsecurity-toolstransformers
corca-ai/awesome-llm-securityRelated projects:
| Repository | Description | Stars |
|---|---|---|
 safellama/plexiglass | A toolkit to detect and protect against vulnerabilities in Large Language Models. | 121 |
| protectai/rebuff | Protects AI applications from prompt injection attacks through multiple layers of defense | 1,124 |
 lostoxygen/llm-confidentiality | Evaluates the confidentiality of Large Language Models integrated with external tools and services | 28 |
 aiplanethub/beyondllm | An open-source toolkit for building and evaluating large language models | 263 |
 ai-hypercomputer/maxtext | A high-performance LLM written in Python/Jax for training and inference on Google Cloud TPUs and GPUs. | 1,529 |
 wgryc/phasellm | A framework for managing and testing large language models to evaluate their performance and optimize user experiences. | 448 |
 melih-unsal/demogpt | A comprehensive toolset for building Large Language Model (LLM) based applications | 1,710 |
 flagai-open/aquila2 | Provides pre-trained language models and tools for fine-tuning and evaluation | 437 |
 deadbits/vigil-llm | A security scanner for Large Language Model prompts to detect potential threats and vulnerabilities | 309 |
 leondz/lm_risk_cards | A set of tools and guidelines for assessing the security vulnerabilities of language models in AI applications | 25 |
 victordibia/llmx | An API that provides a unified interface to multiple large language models for chat fine-tuning | 79 |
 damo-nlp-sg/m3exam | A benchmark for evaluating large language models in multiple languages and formats | 92 |
 internlm/openaoe | Enables users to engage with multiple large language models simultaneously and access their APIs | 253 |
 opengvlab/lamm | A framework and benchmark for training and evaluating multi-modal large language models, enabling the development of AI agents capable of seamless interaction between humans and machines. | 301 |