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.
Jupyter NotebookMIT
Stargazers
- Abdulrhman5
- amnaBooq
- anskarl@pollfish
- CortneyJamesTexas
- crymE-LISEP - Polytechnic of Porto - School of Engineering
- CyberAlbSecOP
- danielsisay
- dnavarromChile
- fnpial
- fruitfoxlu
- hun23
- inistoryYonsei University
- isotropo
- khhung906National Taiwan University
- klncgtyTurkey
- kn1ghtc
- latapiat
- liz6688Beijing Jiaotong University
- mamont0vInspector Security
- monfared01Tehran, Iran
- MoonBirdLin
- muhiminulhasanOneTouch Technologies Ltd
- qdx
- rtrad89UK
- tanujsinghkushwahMetaverse
- Vr3n
- yoyostudyGeorgia Institute of Technology
- zyacub