SCAV: Safety Concept Activation Vector Jailbreak Framework
Project description
This is the code for our NeurIPS 2024 paper <strong>Uncovering Safety Risks of Large Language Models through Concept Activation Vector</strong>.
## Disclaimer
This project may lead to attacks on LLMs and is intended for academic research use only. It is prohibited for illegal purposes. The authors have shared the vulnerabilities with OpenAI and Microsoft.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
scav-1.2.tar.gz
(11.6 kB
view details)
File details
Details for the file scav-1.2.tar.gz.
File metadata
- Download URL: scav-1.2.tar.gz
- Upload date:
- Size: 11.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a69b9e6486abc2312e1e88a443d4e0bbc8571f82fa93a2242d0b1cc2ff0a6c98
|
|
| MD5 |
e20a196c634a2690ef2f3e4f79255270
|
|
| BLAKE2b-256 |
eb80e2493a34104a57c21df7ca23dd58c8a2a11bd2c1c63237c814d2ea087732
|
