terjanq / hack-a-prompt
Tools and our test data developed for the HackAPrompt 2023 competition
☆29Updated last year
Related projects ⓘ
Alternatives and complementary repositories for hack-a-prompt
- ☆62Updated last month
- ☆36Updated this week
- XBOW Validation Benchmarks☆53Updated 2 months ago
- LLM security and privacy☆41Updated last month
- ☆17Updated 10 months ago
- ☆29Updated last month
- ☆63Updated this week
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆233Updated 9 months ago
- ☆24Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆65Updated this week
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publis…☆55Updated last year
- A collection of prompt injection mitigation techniques.☆18Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆47Updated 7 months ago
- Fine-tuning base models to build robust task-specific models☆24Updated 7 months ago
- future-proof vulnerability detection benchmark, based on CVEs in open-source repos☆44Updated last week
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆107Updated 8 months ago
- Challenge Problem #1 - Linux Kernel (NOTE: This code does not reflect the active state of what will be used at competition time, please r…☆51Updated 7 months ago
- ☆22Updated last month
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆405Updated last month
- Dataset for the Tensor Trust project☆33Updated 8 months ago
- Payloads for Attacking Large Language Models☆64Updated 4 months ago
- ☆120Updated 5 months ago
- Python GUI for seeing what's happening inside a fuzzer☆26Updated 3 years ago
- SecLLMHolmes is a generalized, fully automated, and scalable framework to systematically evaluate the performance (i.e., accuracy and rea…☆39Updated 2 weeks ago
- SecGPT: An execution isolation architecture for LLM-based systems☆49Updated 3 weeks ago
- 🪐 A Database of Existing Security Vulnerabilities Patches to Enable Evaluation of Techniques (single-commit; multi-language)☆36Updated last year
- ☆19Updated 6 months ago
- Curation of prompts that are known to be adversarial to large language models☆174Updated last year
- Red-Teaming Language Models with DSPy☆142Updated 7 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…☆313Updated 8 months ago