Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add attack vector & impact info to probes #727

Open
4 tasks
leondz opened this issue Jun 6, 2024 · 0 comments
Open
4 tasks

add attack vector & impact info to probes #727

leondz opened this issue Jun 6, 2024 · 0 comments
Labels
probes Content & activity of LLM probes

Comments

@leondz
Copy link
Owner

leondz commented Jun 6, 2024

  • class-level attack_vector text describing the angle only (or blank, might be a baseline probe)
  • class-level attack_impact text describing what happens if it works, e.g. "private information leaks"
  • define vector_tags list, using attack vectors from e.g. atlasmatrix
  • define impact_tags list, describing impacts if successful, e.g. content safety failures
@leondz leondz added the probes Content & activity of LLM probes label Jun 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
probes Content & activity of LLM probes
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@leondz