conftrace_

privacy neuron

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neuron editing (2) model editing (2) activation value (1) neuron localization (1) memorization capability (1) large language model (1) activation patching (1) personally identifiable information (1) integrated gradient (1) privacy leakage (1)

Papers

Learnable Privacy Neurons Localization in Language Models ACL 2024 Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024 DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models EMNLP 2023