Ace.at_blacked.1.var -

: The framework uses these features to improve the model's resistance to prompt-based attacks that try to bypass concept erasure.

: ACE introduces learnable gating mechanisms in the model's cross-attention layers, which are fine-tuned per concept using these deep feature representations. ace.AT_Blacked.1.var

In the context of the ACE framework, this "deep feature" likely represents a high-dimensional vector in the model's . Key aspects of these features include: : The framework uses these features to improve