sinanw / llm-security-prompt-injectionLinks
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.
☆50Updated 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
Sorting:
- LLM security and privacy☆51Updated last year
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆421Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses☆310Updated last week
- The fastest Trust Layer for AI Agents☆144Updated 4 months ago
- A benchmark for prompt injection detection systems.☆144Updated last month
- Papers about red teaming LLMs and Multimodal models.☆144Updated 4 months ago
- ATLAS tactics, techniques, and case studies data☆82Updated last week
- Dropbox LLM Security research code and results☆237Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆328Updated last week
- ☆165Updated 4 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- A collection of awesome resources related AI security☆332Updated last month
- A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.☆390Updated 2 months ago
- Every practical and proposed defense against prompt injection.☆567Updated 8 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…☆427Updated last year
- A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.☆188Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆172Updated 6 months ago
- Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work☆140Updated 2 weeks ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆31Updated last year
- A collection of prompt injection mitigation techniques.☆24Updated 2 years ago
- 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.☆26Updated last year
- ☆94Updated 11 months ago
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆83Updated 2 weeks ago
- ☆55Updated 5 months ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆319Updated last year
- ☆83Updated last year
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆579Updated last month
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆173Updated 2 years ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆87Updated last year
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.☆63Updated 4 months ago