New ways of breaking app-integrated LLMs
☆2,053Jul 17, 2025Updated 7 months ago
Alternatives and similar repositories for llm-security
Users that are interested in llm-security are comparing it to the libraries listed below
Sorting:
- A curation of awesome tools, documents and projects about LLM Security.☆1,530Aug 20, 2025Updated 6 months ago
- Universal and Transferable Attacks on Aligned Language Models☆4,521Aug 2, 2024Updated 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…☆455Feb 26, 2024Updated 2 years ago
- the LLM vulnerability scanner☆7,088Updated this week
- LLM Prompt Injection Detector☆1,423Aug 7, 2024Updated last year
- OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)☆1,096Feb 22, 2026Updated last week
- Papers and resources related to the security and privacy of LLMs 🤖☆566Jun 8, 2025Updated 8 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆458Jan 31, 2024Updated 2 years ago
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆568Updated this week
- Dropbox LLM Security research code and results☆255May 21, 2024Updated last year
- The Security Toolkit for LLM Interactions☆2,584Dec 15, 2025Updated 2 months ago
- NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.☆5,706Updated this week
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆395Oct 29, 2025Updated 4 months ago
- Making LLMs generate entire projects. Go from idea to runnable project in one step.☆34Feb 12, 2023Updated 3 years ago
- a security scanner for custom LLM applications☆1,134Dec 1, 2025Updated 3 months ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆344Feb 12, 2024Updated 2 years ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆350Oct 17, 2025Updated 4 months ago
- Set of tools to assess and improve LLM security.☆4,036Updated this week
- A guidance language for controlling large language models.☆21,319Feb 13, 2026Updated 2 weeks ago
- The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and eng…☆3,468Updated this week
- Payloads for Attacking Large Language Models☆122Jan 13, 2026Updated last month
- Prompt Injection Primer for Engineers☆555Aug 25, 2023Updated 2 years ago
- Protection against Model Serialization Attacks☆646Feb 18, 2026Updated last week
- Adding guardrails to large language models.☆6,459Updated this week
- A curated list of awesome security tools, experimental case or other interesting things with LLM or GPT.☆644Dec 10, 2025Updated 2 months ago
- Automated Penetration Testing Agentic Framework Powered by Large Language Models☆11,762Updated this week
- ☆698Jul 2, 2025Updated 8 months ago
- Every practical and proposed defense against prompt injection.☆642Feb 22, 2025Updated last year
- An easy-to-use Python framework to generate adversarial jailbreak prompts.☆815Mar 27, 2025Updated 11 months ago
- a CLI that provides a generic automation layer for assessing the security of ML models☆912Jul 18, 2025Updated 7 months ago
- 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading☆9,958Sep 7, 2024Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆106Apr 15, 2024Updated last year
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆635Feb 16, 2026Updated last week
- A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities☆1,693Oct 23, 2024Updated last year
- Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.☆17,929Nov 3, 2025Updated 3 months ago
- OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamical…☆37,444Aug 17, 2024Updated last year
- DSPy: The framework for programming—not prompting—language models☆32,381Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,383Oct 28, 2024Updated last year
- LlamaIndex is the leading document agent and OCR platform☆47,210Updated this week