agencyenterprise / PromptInject
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. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
☆364Updated last year
Alternatives and similar repositories for PromptInject:
Users that are interested in PromptInject are comparing it to the libraries listed below
- ☆545Updated 5 months ago
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆484Updated 7 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆165Updated 4 months ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆192Updated this week
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆325Updated 3 months ago
- Papers about red teaming LLMs and Multimodal models.☆113Updated 5 months ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆637Updated 8 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆380Updated last year
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆336Updated last month
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆296Updated 6 months ago
- Papers and resources related to the security and privacy of LLMs 🤖☆499Updated 5 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆152Updated last month
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆152Updated 4 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆244Updated 10 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆289Updated 7 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆66Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆299Updated 3 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆232Updated 2 months ago
- ☆43Updated 9 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆153Updated last year
- LLM security and privacy☆49Updated 6 months ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆274Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆292Updated last year
- A curation of awesome tools, documents and projects about LLM Security.☆1,202Updated 2 weeks ago
- Red-Teaming Language Models with DSPy☆188Updated 2 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆102Updated 3 months ago
- Improving Alignment and Robustness with Circuit Breakers☆199Updated 7 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆142Updated last week
- ☆97Updated last year
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆109Updated last year