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.
☆37Updated 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
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆176Updated last month
- LLM security and privacy☆47Updated 4 months ago
- Papers about red teaming LLMs and Multimodal models.☆100Updated 3 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 9 months ago
- ☆54Updated 8 months ago
- A collection of prompt injection mitigation techniques.☆20Updated last year
- [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.☆117Updated 2 weeks ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆79Updated 9 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆100Updated this week
- 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.☆23Updated 9 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆108Updated 11 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆148Updated 2 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆63Updated last month
- Payloads for Attacking Large Language Models☆75Updated 7 months ago
- A benchmark for prompt injection detection systems.☆97Updated last month
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆60Updated 10 months ago
- ☆30Updated 3 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆137Updated 2 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆354Updated last year
- The fastest && easiest LLM security guardrails for CX AI Agents and applications.☆123Updated this week
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆267Updated last month
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆36Updated 8 months ago
- ☆84Updated this week
- ☆35Updated 3 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆305Updated 5 months ago
- ☆19Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆41Updated 4 months ago
- Fine-tuning base models to build robust task-specific models☆27Updated 10 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆96Updated last month
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆337Updated last year