dropbox / llm-security
Dropbox LLM Security research code and results
☆210Updated 3 months ago
Related projects: ⓘ
- Every practical and proposed defense against prompt injection.☆310Updated 3 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆299Updated 7 months ago
- Prompt Injection Primer for Engineers☆348Updated last year
- ☆164Updated 8 months ago
- OWASP Foundation Web Respository☆504Updated last week
- Protection against Model Serialization Attacks☆273Updated this week
- Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.☆143Updated 11 months ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆218Updated 7 months ago
- A LLM explicitly designed for getting hacked☆121Updated last year
- OWASP Foundation Web Respository☆199Updated last month
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆360Updated 3 weeks ago
- A benchmark for prompt injection detection systems.☆80Updated last week
- A collection of awesome resources related AI security☆107Updated 5 months ago
- Learn AI security through a series of vulnerable LLM CTF challenges. No sign ups, no cloud fees, run everything locally on your system.☆147Updated 3 weeks ago
- Payloads for Attacking Large Language Models☆56Updated 2 months ago
- OWASP Machine Learning Security Top 10 Project☆69Updated last week
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆103Updated 6 months ago
- A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.☆220Updated last month
- automatically tests prompt injection attacks on ChatGPT instances☆612Updated 9 months ago
- A curated list of large language model tools for cybersecurity research.☆376Updated 5 months ago
- ☆158Updated last month
- Learn about a type of vulnerability that specifically targets machine learning models☆166Updated 3 months ago
- Use AI to Scan Your Code from the Command Line for security and code smells. Bring your own keys. Supports OpenAI and Gemini☆143Updated 6 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆24Updated 3 months ago
- Project LLM Verification Standard☆32Updated 5 months ago
- Vulnerability scanner for AWS customer managed policies using ChatGPT☆142Updated last year
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆112Updated last year
- Test Software for the Characterization of AI Technologies☆212Updated this week
- 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
- Secure Jupyter Notebooks and Experimentation Environment☆52Updated last month