agencyenterprise / PromptInjectLinks
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. π Best Paper Awards @ NeurIPS ML Safety Workshop 2022
β406Updated last year
Alternatives and similar repositories for PromptInject
Users that are interested in PromptInject are comparing it to the libraries listed below
Sorting:
- β604Updated last month
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Promptsβ519Updated 11 months ago
- This repository provides a benchmark for prompt Injection attacks and defensesβ264Updated last month
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!β314Updated 10 months ago
- TAP: An automated jailbreaking method for black-box LLMsβ182Updated 8 months ago
- A benchmark for prompt injection detection systems.β127Updated last month
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]β333Updated 7 months ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Mβ¦β374Updated 7 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.β244Updated 2 weeks ago
- Papers about red teaming LLMs and Multimodal models.β134Updated 2 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]β400Updated 4 months ago
- LLM security and privacyβ50Updated 10 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.β77Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.β167Updated 4 months ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalβ707Updated last year
- A Comprehensive Assessment of Trustworthiness in GPT Modelsβ302Updated 11 months ago
- Papers and resources related to the security and privacy of LLMs π€β527Updated 2 months ago
- The automated prompt injection framework for LLM-integrated applications.β225Updated 11 months ago
- π§ LLMFuzzer - Fuzzing Framework for Large Language Models π§ LLMFuzzer is the first open-source fuzzing framework specifically designed β¦β307Updated last year
- A repository of Language Model Vulnerabilities and Exposures (LVEs).β113Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilityβ165Updated 8 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorchβ274Updated 3 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides aβ¦β64Updated 2 weeks ago
- A curation of awesome tools, documents and projects about LLM Security.β1,363Updated last week
- Whispers in the Machine: Confidentiality in Agentic Systemsβ40Updated 2 weeks ago
- β71Updated last year
- Curation of prompts that are known to be adversarial to large language modelsβ185Updated 2 years ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"β141Updated 4 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheepβs Clothing: Generalized Nested Jailbreak Prompts can Fool Large Langβ¦β128Updated 7 months ago
- We jailbreak GPT-3.5 Turboβs safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20β¦β317Updated last year