sinanw / llm-security-prompt-injection
This project investigates the security of large language models by performing binary classification of a set of input prompts to discover malicious prompts. Several approaches have been analyzed using classical ML algorithms, a trained LLM model, and a fine-tuned LLM model.
☆30Updated 9 months ago
Related projects: ⓘ
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆125Updated 2 weeks ago
- LLM security and privacy☆38Updated 5 months ago
- Payloads for Attacking Large Language Models☆56Updated 2 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆24Updated 3 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆103Updated 6 months ago
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆23Updated 3 months ago
- A benchmark for prompt injection detection systems.☆80Updated last week
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.☆39Updated 2 months ago
- Dropbox LLM Security research code and results☆210Updated 3 months ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆218Updated 7 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆299Updated 7 months ago
- Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.☆143Updated 11 months ago
- Every practical and proposed defense against prompt injection.☆310Updated 3 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆181Updated last month
- Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆36Updated last month
- Papers about red teaming LLMs and Multimodal models.☆66Updated this week
- Learn about a type of vulnerability that specifically targets machine learning models☆166Updated 3 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆106Updated 6 months ago
- A collection of awesome resources related AI security☆107Updated 5 months ago
- SecGPT: An execution isolation architecture for LLM-based systems☆41Updated 3 months ago
- Prompt Injections Everywhere☆68Updated last month
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆366Updated 5 months ago
- ☆33Updated 2 months ago
- Papers and resources related to the security and privacy of LLMs 🤖☆393Updated last week
- A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.☆220Updated last month
- An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]☆169Updated last month
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆293Updated 6 months ago
- OWASP Machine Learning Security Top 10 Project☆69Updated last week
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆72Updated 4 months ago
- ☆357Updated last month