lakeraai / pint-benchmark
A benchmark for prompt injection detection systems.
☆98Updated last month
Alternatives and similar repositories for pint-benchmark:
Users that are interested in pint-benchmark are comparing it to the libraries listed below
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 9 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆60Updated 10 months ago
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆178Updated last month
- Every practical and proposed defense against prompt injection.☆398Updated 2 weeks ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆104Updated last week
- TAP: An automated jailbreaking method for black-box LLMs☆150Updated 3 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆108Updated last year
- Papers about red teaming LLMs and Multimodal models.☆104Updated 3 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆80Updated 9 months ago
- A collection of prompt injection mitigation techniques.☆20Updated last year
- Dropbox LLM Security research code and results☆221Updated 9 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆89Updated 2 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆44Updated 4 months ago
- [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.☆120Updated this week
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆273Updated last month
- ☆511Updated 3 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆102Updated last year
- Project LLM Verification Standard☆40Updated 11 months ago
- LLM security and privacy☆47Updated 4 months ago
- Payloads for Attacking Large Language Models☆75Updated 8 months ago
- A text embedding viewer for the Jupyter environment☆19Updated last year
- All things specific to LLM Red Teaming Generative AI☆23Updated 4 months ago
- ☆85Updated last week
- This project investigates the security of large language models by performing binary classification of a set of input prompts to discover…☆37Updated 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…☆341Updated last year
- ☆54Updated 8 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆355Updated last year
- Red-Teaming Language Models with DSPy☆171Updated last month
- ATLAS tactics, techniques, and case studies data☆57Updated 5 months ago
- ☆42Updated 7 months ago