tpai / gandalf-prompt-injection-writeup
A writeup for the Gandalf prompt injection game.
☆36Updated last year
Related projects ⓘ
Alternatives and complementary repositories for gandalf-prompt-injection-writeup
- Codebase of https://arxiv.org/abs/2410.14923☆27Updated 3 weeks ago
- My inputs for the LLM Gandalf made by Lakera☆36Updated last year
- Payloads for Attacking Large Language Models☆63Updated 4 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆72Updated 5 months ago
- A benchmark for prompt injection detection systems.☆86Updated 2 months ago
- Fine-tuning base models to build robust task-specific models☆24Updated 7 months ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆259Updated last month
- A collection of prompt injection mitigation techniques.☆17Updated last year
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆142Updated 2 months ago
- ☆38Updated 4 months ago
- ☆402Updated 2 months ago
- Dropbox LLM Security research code and results☆216Updated 5 months ago
- [Corca / ML] Automatically solved Gandalf AI with LLM☆46Updated last year
- Tools and our test data developed for the HackAPrompt 2023 competition☆29Updated last year
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆308Updated 8 months ago
- LLM security and privacy☆40Updated 3 weeks ago
- Red-Teaming Language Models with DSPy☆142Updated 7 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆227Updated last month
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆397Updated last month
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆46Updated 6 months ago
- Whispers in the Machine: Confidentiality in LLM-integrated Systems☆28Updated last week
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆212Updated last month
- 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.☆15Updated 5 months ago
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆193Updated 8 months ago
- The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.☆19Updated last week
- ☆61Updated last month
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆231Updated 9 months ago
- Papers about red teaming LLMs and Multimodal models.☆78Updated last month
- Code for the website www.jailbreakchat.com☆74Updated last year
- Every practical and proposed defense against prompt injection.☆339Updated 5 months ago