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.
☆39Updated 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
Sorting:
- This repository provides a benchmark for prompt Injection attacks and defenses☆196Updated 2 weeks ago
- LLM security and privacy☆49Updated 7 months ago
- ☆100Updated 2 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆154Updated last week
- A collection of prompt injection mitigation techniques.☆22Updated last year
- ☆62Updated 10 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆167Updated 5 months ago
- ☆62Updated 5 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆66Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆156Updated last month
- Papers about red teaming LLMs and Multimodal models.☆115Updated 5 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 11 months ago
- A benchmark for prompt injection detection systems.☆110Updated this week
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆46Updated 6 months ago
- 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.☆23Updated last year
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆45Updated 11 months ago
- Top 10 for Agentic AI (AI Agent Security)☆99Updated 2 months ago
- Payloads for Attacking Large Language Models☆83Updated 10 months ago
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆32Updated 11 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆118Updated last month
- ☆32Updated 6 months ago
- The fastest Trust Layer for AI Agents☆133Updated 2 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆79Updated 3 months ago
- source for llmsec.net☆15Updated 9 months ago
- All things specific to LLM Red Teaming Generative AI☆24Updated 6 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆109Updated last year
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆50Updated 9 months ago
- ☆39Updated last week
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆55Updated 2 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆152Updated 4 months ago