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

March 05, 2020 ยท Declared Dead ยท ๐Ÿ› European Conference on Computer Vision

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Aditya Golatkar, Alessandro Achille, Stefano Soatto arXiv ID 2003.02960 Category cs.LG: Machine Learning Cross-listed cs.CV, cs.IT, stat.ML Citations 233 Venue European Conference on Computer Vision Last Checked 3 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted