rebuff
Prompt shield
Protects AI applications from prompt injection attacks through multiple layers of defense
LLM Prompt Injection Detector
1k stars
14 watching
81 forks
Language: TypeScript
last commit: 4 months ago
Linked from 1 awesome list
llmllmopsprompt-engineeringprompt-injectionpromptssecurity
corca-ai/awesome-llm-securityRelated projects:
| Repository | Description | Stars |
|---|---|---|
| protectai/llm-guard | A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities. | 1,242 |
 promptslab/openai-detector | An AI classifier designed to determine whether text is written by humans or machines. | 122 |
 agencyenterprise/promptinject | A framework for analyzing the robustness of large language models to adversarial prompt attacks | 309 |
 jthack/pipe | A guide to help developers understand and mitigate the security risks of prompt injection in AI-powered applications and features. | 359 |
 limmen/gym-optimal-intrusion-response | An environment for training artificial intelligence models to respond optimally to security threats in computer networks | 21 |
 may215/koa-protect | A security module for Koa applications that provides proactive protection against common security threats. | 19 |
 mcaptcha/mcaptcha | A CAPTCHA system with proof-of-work based rate limiting and token-based validation | 1,718 |
 safellama/plexiglass | A toolkit to detect and protect against vulnerabilities in Large Language Models. | 121 |
 prosopo/captcha | Protects websites from bots and automated abuse by solving a challenge without collecting user data | 48 |
 hassio-addons/addon-tor | Protects Home Assistant instance access by routing requests through the Tor network | 52 |
 satrobit/lua-resty-ddos | A Lua-based module for detecting and mitigating bot traffic in web applications | 16 |
 matthutchinson/acts_as_textcaptcha | Spam protection for Rails applications using text-based logic question captchas. | 56 |
 ethz-spylab/rlhf_trojan_competition | Detecting backdoors in language models to prevent malicious AI usage | 107 |
 secdec/attack-surface-detector-burp | Identifies web app endpoints and parameters to help detect vulnerabilities | 98 |
 ai-prompt-genius/ai-prompt-genius | A Chrome extension that allows users to curate and manage a custom library of AI prompts. | 1,100 |