Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations

About

We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions and can be extended to ensure forgetting in the activations of the network. We introduce a new bound on how much information can be extracted per query about the forgotten cohort from a black-box network for which only the input-output behavior is observed. The proposed forgetting procedure has a deterministic part derived from the differential equations of a linearized version of the model, and a stochastic part that ensures information destruction by adding noise tailored to the geometry of the loss landscape. We exploit the connections between the activation and weight dynamics of a DNN inspired by Neural Tangent Kernels to compute the information in the activations.

Aditya Golatkar, Alessandro Achille, Stefano Soatto• 2020

Related benchmarks

TaskDatasetResultRank
Machine UnlearningMNIST
Model Accuracy88.88
56
Class UnlearningCIFAR-10 (test)--
42
Selective UnlearningLacuna 10 (test)
Test Error (mean)1.87
36
Class UnlearningCIFAR-10--
28
Class UnlearningLacuna 10 (test)
Test Error (Mean)1.78
27
Resolving ConfusionLacuna-5 (test)
Test Error12.87
27
Selective UnlearningCIFAR-10
Test Error21.23
27
Class UnlearningLacuna-10
Test Error3.33
27
Machine UnlearningCIFAR-10
Accuracy62.81
24
Machine UnlearningUCI Adult
Accuracy84.34
24
Showing 10 of 26 rows

Other info

Follow for update