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.
☆36Updated last year
Alternatives and similar repositories for llm-security-prompt-injection:
Users that are interested in llm-security-prompt-injection are comparing it to the libraries listed below
- LLM security and privacy☆43Updated 3 months ago
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆163Updated this week
- ☆47Updated 6 months ago
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.☆47Updated last month
- Papers about red teaming LLMs and Multimodal models.☆91Updated last month
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆89Updated 3 weeks ago
- A collection of automated evaluators for assessing jailbreak attempts.☆92Updated last week
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆74Updated this week
- Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"☆36Updated 3 months ago
- SecGPT: An execution isolation architecture for LLM-based systems☆57Updated last month
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆35Updated 7 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆108Updated 10 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆39Updated 2 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆323Updated 10 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆247Updated 3 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆339Updated 11 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 7 months ago
- A collection of prompt injection mitigation techniques.☆20Updated last year
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆274Updated 3 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆53Updated 9 months ago
- ☆18Updated last year
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆31Updated 7 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆133Updated last month
- Learn about a type of vulnerability that specifically targets machine learning models☆210Updated 7 months ago
- A prompt injection game to collect data for robust ML research☆49Updated 3 weeks ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆128Updated last month
- Papers and resources related to the security and privacy of LLMs 🤖☆467Updated last month
- LLM | Security | Operations in one github repo with good links and pictures.☆24Updated 2 weeks ago
- ☆42Updated 8 months ago
- ☆39Updated 5 months ago