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
β427Updated last year
Alternatives and similar repositories for PromptInject
Users that are interested in PromptInject are comparing it to the libraries listed below
Sorting:
- β639Updated 3 months ago
- This repository provides a benchmark for prompt injection attacks and defensesβ310Updated last week
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Promptsβ533Updated last year
- TAP: An automated jailbreaking method for black-box LLMsβ194Updated 10 months ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!β327Updated last week
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]β357Updated 9 months ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Mβ¦β388Updated 9 months ago
- The automated prompt injection framework for LLM-integrated applications.β235Updated last year
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalβ760Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.β328Updated 2 weeks ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.β87Updated last year
- Papers about red teaming LLMs and Multimodal models.β144Updated 5 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]β438Updated 6 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.β172Updated 6 months ago
- β‘ Vigil β‘ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputsβ421Updated last year
- A benchmark for prompt injection detection systems.β144Updated 2 months ago
- Papers and resources related to the security and privacy of LLMs π€β536Updated 4 months ago
- LLM security and privacyβ51Updated last year
- A Comprehensive Assessment of Trustworthiness in GPT Modelsβ306Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorchβ293Updated 5 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilityβ166Updated 10 months ago
- β83Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides aβ¦β69Updated last month
- The official implementation of our NAACL 2024 paper "A Wolf in Sheepβs Clothing: Generalized Nested Jailbreak Prompts can Fool Large Langβ¦β141Updated last month
- A curation of awesome tools, documents and projects about LLM Security.β1,431Updated 2 months ago
- Awesome LLM Jailbreak academic papersβ111Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)β91Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".β60Updated last year
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacksβ55Updated 5 months ago
- Whispers in the Machine: Confidentiality in Agentic Systemsβ41Updated 3 weeks ago