Skip to content

v1.1.1
Compare
Choose a tag to compare
@RomiconEZ RomiconEZ released this 16 Dec 12:43
· 4 commits to release since this release
v1.1.1
35382c6
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's new

  • Enhanced prompts for attacking and judging models in base64, harmful behavior, sycophancy, ethical compliance attacks
  • Added new Logical inconsistencies attack
  • Added more jailbreaks into DAN and UCAR datasets, all datasets in parquet format now
  • Included a practical example for testing chatbots within WhatsApp
  • Various small bug fixes and optimizations across the framework

We hope these changes enhance your capabilities in conducting effective LLM Red teaming exercises.

If you have any feedback or questions, feel free to reach out!

Assets 2
Loading