lve-org / lveLinks
A repository of Language Model Vulnerabilities and Exposures (LVEs).
☆112Updated last year
Alternatives and similar repositories for lve
Users that are interested in lve are comparing it to the libraries listed below
Sorting:
- A benchmark for prompt injection detection systems.☆121Updated 2 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆202Updated last week
- ☆119Updated last month
- Risks and targets for assessing LLMs & LLM vulnerabilities☆31Updated last year
- Dropbox LLM Security research code and results☆227Updated last year
- Red-Teaming Language Models with DSPy☆202Updated 5 months ago
- LLM security and privacy☆48Updated 8 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆88Updated last year
- A collection of prompt injection mitigation techniques.☆22Updated 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…☆393Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆59Updated 4 months ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆245Updated last month
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆71Updated last year
- future-proof vulnerability detection benchmark, based on CVEs in open-source repos☆58Updated this week
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆395Updated last year
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆41Updated 3 weeks ago
- Papers about red teaming LLMs and Multimodal models.☆125Updated last month
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆286Updated last year
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆518Updated 3 weeks ago
- ☆137Updated 2 months ago
- ☆34Updated 8 months ago
- Code for the paper "Defeating Prompt Injections by Design"☆40Updated 3 weeks ago
- The fastest Trust Layer for AI Agents☆138Updated last month
- ☆65Updated 5 months ago
- ☆45Updated 11 months ago
- Guardrails for secure and robust agent development☆313Updated last month
- This project investigates the security of large language models by performing binary classification of a set of input prompts to discover…☆41Updated last year
- Every practical and proposed defense against prompt injection.☆495Updated 4 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆320Updated 5 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆111Updated last year