Script Kitty OS
- 13 followers
- United States of America
- https://scriptkittyos.com
- @ScriptKittyOS
- dev@scriptkittyos.com
Popular repositories Loading
-
HolyTrinity-Benchmark
HolyTrinity-Benchmark PublicAdversarial security benchmark for agent authorization: does a compromised agent's policy-violating proposal become an unauthorized external effect? 73 trials, nine families, an independent oracle,…
Repositories
Showing 1 of 1 repositories
- HolyTrinity-Benchmark Public
Adversarial security benchmark for agent authorization: does a compromised agent's policy-violating proposal become an unauthorized external effect? 73 trials, nine families, an independent oracle, per-mechanism ablation, confidence intervals. 0 unauthorized effects in 61 attack trials (95% CI [0.0%, 5.9%]). Reproduction is partial.
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…