CoChat

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

Open access
Golatkar, Aditya, Achille, Alessandro, Soatto, Stefano · 2020 · Lecture Notes in Computer Science

The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-030-58526-6_23

Cites

38 of 38 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 38 references

Research works printed but not linked: 3

  1. Achille, A., Soatto, S.: Emergence of invariance and disentanglement in deep representations. J. Mach. Learn. Res. 19(1), 1947–1980 (2018)
  2. Ginart, A., Guan, M., Valiant, G., Zou, J.Y.: Making AI forget you: data deletion in machine learning. In: Advances in Neural Information Processing Systems, pp. 3513–3526 (2019)
  3. Mirzasoleiman, B., Karbasi, A., Krause, A.: Deletion-robust submodular maximization: data summarization with “the right to be forgotten”. In: International Conference on Machine Learning, pp. 2449–2458 (2017)

Cited by

See all 122

Metadata

Authors
Golatkar, A., Achille, A., & Soatto, S.
Affiliations
University of California, Los Angeles (US)
Corresponding author
Golatkar, Aditya
Venue
Lecture Notes in Computer Science
Published
2020
Pages
383-398
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
OpenAlex
W3010154811
Cited by
122
References
38
Citations by year
2026: 18 · 2025: 25 · 2024: 29 · 2023: 24 · 2022: 15 · 2021: 8 · 2020: 3
FWCI
4.77
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Office of Naval Research (N00014-19-1-2229, ONR-N00014, N00014-19, N00014)
  • Army Research Office (W911NF-17, W911NF-17-1-0304, W911NF, ARO W911NF-17-1-0304)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
Keywords
deep neural network, black-box attacks, information extraction, differential privacy, noise injection, loss landscape, neural tangent kernel, weight dynamics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations. https://app.cochat.ai/papers/10.1007/978-3-030-58526-6_23
The paper
Golatkar, A., Achille, A., & Soatto, S. (2020). Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-030-58526-6_23

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.