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.
☆34Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for llm-security-prompt-injection
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆146Updated 2 months ago
- LLM security and privacy☆41Updated last month
- Papers about red teaming LLMs and Multimodal models.☆78Updated last month
- Risks and targets for assessing LLMs & LLM vulnerabilities☆25Updated 5 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆107Updated 8 months ago
- Payloads for Attacking Large Language Models☆64Updated 4 months ago
- A benchmark for prompt injection detection systems.☆87Updated 2 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆73Updated 6 months ago
- SecGPT: An execution isolation architecture for LLM-based systems☆49Updated 3 weeks ago
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.☆44Updated last week
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆59Updated 3 months ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆315Updated 9 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆65Updated this week
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆232Updated last month
- ☆38Updated 4 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆220Updated 2 months ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆233Updated 9 months ago
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆27Updated 6 months ago
- A collection of awesome resources related AI security☆131Updated 8 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆110Updated 2 months ago
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆121Updated last year
- Learn about a type of vulnerability that specifically targets machine learning models☆183Updated 5 months ago
- A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.☆246Updated last month
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆28Updated 5 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆119Updated 8 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆25Updated 3 weeks ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆34Updated 3 weeks ago
- A collection of prompt injection mitigation techniques.☆18Updated last year
- Tree of Attacks (TAP) Jailbreaking Implementation☆95Updated 9 months ago
- The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".☆245Updated 3 weeks ago