12 citations · 18 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 4 cited
Deceptive Alignment Monitoring
Andres Carranza, Dhruv Pai, Rylan Schaeffer +2
As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the mo…
cs.LG2023
FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation
Dhruv Pai, Andres Carranza, Rylan Schaeffer +2
We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the…