Fine-tuning base models to build robust task-specific models
☆36Apr 11, 2024Updated 2 years ago
Alternatives and similar repositories for prompt-injection-defense
Users that are interested in prompt-injection-defense are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins☆29Jul 29, 2024Updated 2 years ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆39Jul 2, 2026Updated 4 months ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆22Mar 25, 2024Updated 2 years ago
- ☆13Apr 6, 2026Updated 7 months ago
- ☆31Jul 14, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆13Mar 22, 2025Updated last year
- ☆21Mar 19, 2023Updated 3 years ago
- ☆41Dec 19, 2024Updated last year
- The most comprehensive and accurate LLM jailbreak attack benchmark by far☆22Mar 22, 2025Updated last year
- ☆30Aug 12, 2026Updated 3 months ago
- ☆48May 9, 2024Updated 2 years ago
- ☆16Dec 28, 2024Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆471Jan 22, 2025Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆517Sep 27, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆15Dec 16, 2024Updated last year
- ☆10Dec 14, 2023Updated 2 years ago
- ☆206Nov 26, 2023Updated 2 years ago
- The automated prompt injection framework for LLM-integrated applications.☆281Sep 12, 2024Updated 2 years ago
- Explore, Establish, Exploit: Red Teaming Language Models from Scratch☆15Jun 21, 2023Updated 3 years ago
- Red Queen Dataset and data generation template☆29Dec 26, 2025Updated 10 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆97Sep 1, 2025Updated last year
- Repository for "StrongREJECT for Empty Jailbreaks" paper☆162Nov 3, 2024Updated 2 years ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆28Nov 25, 2022Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆11Sep 17, 2023Updated 3 years ago
- Towards Efficient and Effective Adversarial Training, NeurIPS 2021☆15Feb 15, 2022Updated 4 years ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆75Oct 23, 2024Updated 2 years ago
- ☆20Oct 20, 2024Updated 2 years ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- A new algorithm that formulates jailbreaking as a reasoning problem.☆26Jul 2, 2025Updated last year
- In-context Example Selection with Influences☆15May 12, 2023Updated 3 years ago
- ☆821Jul 2, 2025Updated last year
- LLM prompt attacks for hacker CTFs via CTFd.☆15Dec 17, 2023Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An Ra2 observer deeply inspired by ra2viewer.☆11Mar 31, 2025Updated last year
- [ICML 2026] ReCAP-Agent is an open stack for generating, evaluating, and training CAPTCHA-capable GUI agents.☆14Aug 1, 2026Updated 3 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 2025Updated last year
- ☆25Jan 17, 2025Updated last year
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆60Apr 25, 2026Updated 6 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆167Nov 30, 2024Updated last year
- Make RA2 matches look cooler!☆12Mar 26, 2025Updated last year
Are these results useful?