#

llm-security

Here are 43 public repositories matching this topic...

wangywUST / OutputJailbreak

Repository for our paper "Frustratingly Easy Jailbreak of Large Language Models via Output Prefix Attacks". https://www.researchsquare.com/article/rs-4385503/latest

nlp jailbreak llm llm-security

Updated Jun 19, 2024
Jupyter Notebook

nodite / llm-guard-ts

The Security Toolkit for LLM Interactions (TS version)

typescript transformers security-tools adversarial-machine-learning large-language-models llm prompt-engineering chatgpt llmops prompt-injection llm-security

Updated Jan 5, 2024

CyberAlbSecOP / MINOTAUR_Impossible_GPT_Security_Challenge

MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge, Impossible GPT Security, Prompts Cybersecurity, Prompting Vulnerabilities, FlowGPT, Secure Prompting, Secure LLMs, Prompt Hacker, Cutting-edge Ai Security, Unbreakable GPT Agent, Anti GPT Leak, System Prompt Security.

cyber-security security-challenge ai-security prompt-engineering prompt-injection gpt-security llm-security ai-jailbreak ai-jailbreak-prompts prompt-security system-prompt super-prompt prompt-security-challenge ai-cyber-security gpts-security flow-gpt

Updated Mar 27, 2024

awesome-software / llm-attacks

Universal and Transferable Attacks on Aligned Language Models

Updated Sep 19, 2023
Python

mickymultani / TestingGemma2B

Evaluation of Google's Instruction Tuned Gemma-2B, an open-source Large Language Model (LLM). Aimed at understanding the breadth of the model's knowledge, its reasoning capabilities, and adherence to ethical guardrails, this project presents a systematic assessment across a diverse array of domains.

gemma responsible-ai huggingface-transformers llm llms llmops genai llm-security llm-inference genai-usecase largelanguagemodels gemma-2b

Updated Feb 26, 2024
Jupyter Notebook

matthernet / LLM-security-check

CLI tool that uses the Lakera API to perform security checks in LLM inputs

ai artificial-intelligence ai-security large-language-models llm llm-security

Updated Mar 13, 2024
Python

lastlayer / last-layer-vercel

Example of running last_layer with FastAPI on vercel

llm-security llm-privacy llm-guard llm-guardrails

Updated Apr 5, 2024
Python

rohilrg / CatchPromptInjection

This repo focus on how to deal with prompt injection problem faced by LLMs

openai-api transformers-models llm langchain prompt-injection llm-security

Updated Oct 19, 2023
Python

nagababumo / Red-Teaming-LLM-Applications

jailbreak red-teaming giskard prompt-injection llm-security

Updated Jun 21, 2024
Jupyter Notebook

minuva / fast-prompt-attack-detect

User prompt attack detection system

nlp api jailbreak security-tools fastapi llm-security llm-local llm-vulnerabilities llm-guardrails

Updated May 31, 2024
Python

Awesome-LLMs-ICLR-24

azminewasi / Awesome-LLMs-ICLR-24

It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.

pretrained-models pretrained-weights pretrained-language-model large-language-models llm llms llmops large-language-model llm-serving llm-prompting llm-agent llm-security llm-training llm-inference llm-framework llm-privacy llm-evaluation large-language-models-for-graph-learning large-language-models-and-translation-systems

Updated Apr 4, 2024

balavenkatesh3322 / guardrails-demo

LLM Security Project with Llama Guard

security attack-defense llm aisecurity generative-ai llmops llm-security llama-2 prompt-injection-tool llama-guard

Updated Feb 18, 2024
Python

awesome-software / llm-guard

The Security Toolkit for LLM Interactions

Updated Sep 21, 2023
Python

CommissarSilver / TraWiC

Trained Without My Consent (TraWiC): Detecting Code Inclusion In Language Models Trained on Code

intellectual-property llm-security llm-training code-llms llm-evaluation

Updated Jun 20, 2024
Python

pdparchitect / llm-hacking-database

This repository contains various attack against Large Language Models.

security hacking llm llm-security

Updated May 21, 2024

lakeraai / chainguard

Guard your LangChain applications against prompt injection with Lakera ChainGuard.

llm langchain prompt-injection langchain-python llm-security

Updated Apr 17, 2024
Python

last_layer

arekusandr / last_layer

Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️

jailbreak security-tools large-language-models prompt-engineering chatgpt-prompts llm-security llm-local llm-guard llm-guardrails

Updated Jun 26, 2024
Python

microsoft / BIPIA

A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.

Updated Apr 15, 2024
Python

M507 / HackMeGPT

Vulnerable LLM Application

gandalf security-tools damn-vulnerable prompt-engineering prompt-injection llm-security jailbreak-prompt vulnerable-llm-application

Updated Jan 1, 2024
Python

LostOxygen / llm-confidentiality

Whispers in the Machine: Confidentiality in LLM-integrated Systems

security machine-learning framework deep-learning transformers openai prompt-toolkit gpt confidentiality systems-security llm prompt-engineering chatgpt prompt-injection llm-security

Updated Jun 25, 2024
Python

Improve this page

Add a description, image, and links to the llm-security topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the llm-security topic, visit your repo's landing page and select "manage topics."