vigil-llm
Prompt Scanner
A security scanner for Large Language Model prompts to detect potential threats and vulnerabilities
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
326 stars
11 watching
36 forks
Language: Python
last commit: about 1 year ago
Linked from 2 awesome lists
adversarial-attacksadversarial-machine-learninglarge-language-modelsllm-securityllmopsprompt-injectionsecurity-toolsyara-scanner
corca-ai/awesome-llm-security
briland/llm-security-and-privacyRelated projects:
| Repository | Description | Stars |
|---|---|---|
 safellama/plexiglass | A toolkit to detect and protect against vulnerabilities in Large Language Models. | 122 |
 protectai/llm-guard | A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities. | 1,296 |
| protectai/rebuff | Protects AI applications from prompt injection attacks through multiple layers of defense | 1,144 |
 dicklesworthstone/swiss_army_llama | A FastAPI service that facilitates semantic text search using precomputed embeddings and advanced similarity measures. | 947 |
 victordibia/llmx | An API that provides a unified interface to multiple large language models for chat fine-tuning | 79 |
 13o-bbr-bbq/machine_learning_security | An open-source project that explores the intersection of machine learning and security to develop tools for detecting vulnerabilities in web applications. | 1,987 |
 lennolium/swiftguard | A macOS application that detects and prevents unauthorized USB device activity on a computer. | 337 |
 xverse-ai/xverse-7b | A multilingual large language model developed by XVERSE Technology Inc. | 50 |
 m0nad/hellraiser | Scans networks to identify vulnerabilities by correlating CPEs with CVEs using an API | 562 |
 vernamlab/medusa | Automated attack synthesis tool for discovering vulnerabilities in CPU architecture and cryptographic protocols | 18 |
 luogen1996/lavin | An open-source implementation of a vision-language instructed large language model | 513 |
 ddzipp/autoaudit | An application of Large Language Models to improve cybersecurity through enhanced threat detection and response capabilities | 264 |
 belane/linux-soft-exploit-suggester | A script to identify vulnerabilities in software packages on Linux systems | 222 |
 qcri/llmebench | A benchmarking framework for large language models | 81 |