sinanw / llm-security-prompt-injection
This project investigates the security of large language models by performing binary classification of a set of input prompts to discover malicious prompts. Several approaches have been analyzed using classical ML algorithms, a trained LLM model, and a fine-tuned LLM model.
☆38Updated last year
Alternatives and similar repositories for llm-security-prompt-injection:
Users that are interested in llm-security-prompt-injection are comparing it to the libraries listed below
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 10 months ago
- A benchmark for prompt injection detection systems.☆99Updated last month
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆182Updated 2 months ago
- LLM security and privacy☆48Updated 5 months ago
- ☆41Updated 4 months ago
- ☆57Updated 9 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆116Updated last week
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆43Updated 5 months ago
- ☆42Updated 8 months ago
- Red-Teaming Language Models with DSPy☆175Updated last month
- Papers about red teaming LLMs and Multimodal models.☆105Updated 4 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆153Updated 3 months ago
- A collection of prompt injection mitigation techniques.☆20Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆148Updated 3 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆143Updated this week
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆39Updated 9 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆81Updated 10 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆108Updated last year
- Dataset for the Tensor Trust project☆39Updated 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…☆352Updated last year
- ☆31Updated 4 months ago
- Code to break Llama Guard☆31Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆289Updated 2 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆105Updated 2 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆63Updated 11 months ago
- A prompt injection game to collect data for robust ML research☆55Updated 2 months ago
- Payloads for Attacking Large Language Models☆77Updated 8 months ago
- ☆90Updated last month
- Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"☆41Updated 6 months ago
- LLM | Security | Operations in one github repo with good links and pictures.☆24Updated 3 months ago