PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. π Best Paper Awards @ NeurIPS ML Safety Workshop 2022
β530Apr 27, 2026Updated 6 months ago
Alternatives and similar repositories for PromptInject
Users that are interested in PromptInject are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- the LLM vulnerability scannerβ10,114Updated this week
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Promptsβ609Feb 27, 2026Updated 8 months ago
- New ways of breaking app-integrated LLMsβ2,153Jul 17, 2025Updated last year
- β30Feb 5, 2024Updated 2 years ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Mβ¦β471Jan 22, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- This repository provides a benchmark for prompt injection attacks and defenses in LLMsβ517Sep 27, 2026Updated last month
- Universal and Transferable Attacks on Aligned Language Modelsβ4,867Aug 2, 2024Updated 2 years ago
- LLM Prompt Injection Detectorβ1,534Aug 7, 2024Updated 2 years ago
- β821Jul 2, 2025Updated last year
- A curation of awesome tools, documents and projects about LLM Security.β1,722Aug 20, 2025Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".β75Oct 23, 2024Updated 2 years ago
- The automated prompt injection framework for LLM-integrated applications.β280Sep 12, 2024Updated 2 years ago
- π§ LLMFuzzer - Fuzzing Framework for Large Language Models π§ LLMFuzzer is the first open-source fuzzing framework specifically designed β¦β389Feb 12, 2024Updated 2 years ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalβ1,127Aug 16, 2024Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available β’ AdRun AI, ML, and HPC workloads on powerful cloud GPUsβwithout limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Curation of prompts that are known to be adversarial to large language modelsβ194Feb 12, 2023Updated 3 years ago
- β‘ Vigil β‘ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputsβ511Jan 31, 2024Updated 2 years ago
- a security scanner for custom LLM applicationsβ1,295Dec 1, 2025Updated 11 months ago
- Make your GenAI Apps Safe & Secure Test & harden your system promptβ719Aug 19, 2026Updated 3 months ago
- TAP: An automated jailbreaking method for black-box LLMsβ255Dec 10, 2024Updated last year
- β12May 14, 2024Updated 2 years ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"β182Feb 20, 2024Updated 2 years ago
- Repository for "StrongREJECT for Empty Jailbreaks" paperβ162Nov 3, 2024Updated 2 years ago
- Dropbox LLM Security research code and resultsβ259May 21, 2024Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available β’ AdRun AI, ML, and HPC workloads on powerful cloud GPUsβwithout limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Every practical and proposed defense against prompt injection.β742Feb 22, 2025Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]β400Jan 23, 2025Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignmentβ112Mar 8, 2024Updated 2 years ago
- Open-source AI red teaming toolkit from Microsoft. Test generative AI systems with automated scans, adaptive multi-turn attacks, and a weβ¦β4,968Updated this week
- β206Nov 26, 2023Updated 2 years ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"β62Aug 8, 2024Updated 2 years ago
- The Security Toolkit for LLM Interactionsβ3,221Jul 8, 2026Updated 4 months ago
- Fine-tuning base models to build robust task-specific modelsβ36Apr 11, 2024Updated 2 years ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]β701Apr 4, 2025Updated last year
- Open source password manager - Proton Pass β’ AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- An easy-to-use Python framework to generate adversarial jailbreak prompts.β948Sep 1, 2026Updated 2 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilitiesβ36May 27, 2024Updated 2 years ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Promptingβ22Mar 25, 2024Updated 2 years ago
- A framework to evaluate the generalization capability of safety alignment for LLMsβ626Oct 9, 2025Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)β89May 14, 2024Updated 2 years ago
- Explore, Establish, Exploit: Red Teaming Language Models from Scratchβ15Jun 21, 2023Updated 3 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"β1,860Jun 17, 2025Updated last year
Are these results useful?