ethz-spylab / agentdojoLinks
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
☆188Updated this week
Alternatives and similar repositories for agentdojo
Users that are interested in agentdojo are comparing it to the libraries listed below
Sorting:
- ☆65Updated 11 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆69Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆158Updated 2 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆173Updated 6 months ago
- Papers about red teaming LLMs and Multimodal models.☆123Updated 3 weeks ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆130Updated 2 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆316Updated 5 months ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆230Updated 3 weeks ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆127Updated 3 weeks ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆22Updated 7 months ago
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆164Updated last month
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆37Updated last month
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆245Updated last month
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆51Updated 10 months ago
- ☆112Updated last week
- Agent Security Bench (ASB)☆89Updated last week
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- ☆100Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆80Updated 8 months ago
- ☆58Updated 6 months ago
- A benchmark for prompt injection detection systems.☆118Updated last month
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆49Updated 8 months ago
- ☆45Updated 10 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆152Updated 6 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆157Updated last year
- LLM security and privacy☆48Updated 8 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆56Updated 3 months ago
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆49Updated last month
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆359Updated 2 months ago