Fine-tuning base models to build robust task-specific models
☆34Apr 11, 2024Updated last year
Alternatives and similar repositories for prompt-injection-defense
Users that are interested in prompt-injection-defense are comparing it to the libraries listed below
Sorting:
- ☆28Mar 20, 2024Updated last year
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆20Mar 25, 2024Updated last year
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆13Dec 16, 2024Updated last year
- ☆31Jul 14, 2023Updated 2 years ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 2025Updated 10 months ago
- Red Queen Dataset and data generation template☆27Dec 26, 2025Updated 2 months ago
- Code repository for CVPR2024 paper 《Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness》☆25May 29, 2024Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆396Oct 29, 2025Updated 4 months ago
- The most comprehensive and accurate LLM jailbreak attack benchmark by far☆22Mar 22, 2025Updated 11 months ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆430Jan 22, 2025Updated last year
- A new algorithm that formulates jailbreaking as a reasoning problem.☆26Jul 2, 2025Updated 8 months ago
- ☆48May 9, 2024Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆59Jan 15, 2025Updated last year
- Implementation of paper 'Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing'☆23Jun 9, 2024Updated last year
- The automated prompt injection framework for LLM-integrated applications.☆255Sep 12, 2024Updated last year
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated 9 months ago
- LLM Prompt Injection Detection API Service PoC.☆10Nov 14, 2025Updated 3 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆69Oct 23, 2024Updated last year
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆50Nov 5, 2025Updated 4 months ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆28Nov 25, 2022Updated 3 years ago
- ☆197Nov 26, 2023Updated 2 years ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆34Nov 8, 2024Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆72Feb 9, 2026Updated last month
- Shuffle your YouTube playlists☆12Mar 2, 2026Updated last week
- Data sets and ML models versioning example from DVC get started☆10Jun 4, 2024Updated last year
- ☆40May 17, 2025Updated 9 months ago
- estruct traverses javascript projects and maps all the dependencies and relationships to a JSON. the output can be used to build network …☆12Aug 22, 2021Updated 4 years ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆83Nov 3, 2024Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆34Aug 16, 2024Updated last year
- Example code of [Tianchi AAAI2022 Security AI Challenger Program Phase 8]☆22Feb 9, 2022Updated 4 years ago
- ☆37Oct 2, 2024Updated last year
- Repository for "StrongREJECT for Empty Jailbreaks" paper☆152Nov 3, 2024Updated last year
- ☆10Sep 24, 2021Updated 4 years ago
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆39Jan 17, 2025Updated last year
- official code for unigame☆19Nov 26, 2025Updated 3 months ago
- ☆12May 6, 2022Updated 3 years ago
- Tools and our test data developed for the HackAPrompt 2023 competition☆47Oct 20, 2023Updated 2 years ago
- ☆701Jul 2, 2025Updated 8 months ago
- ☆12Nov 23, 2025Updated 3 months ago