Papers › Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

12 Nov 2019CVPR 2020 6arXiv:1911.04933archive 2025-07-28

Aditya Golatkar, Alessandro Achille, Stefano Soatto

We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be gleaned by probing deep into its weights. We propose a method for "scrubbing'" the weights clean of information about a particular set of training data. The method does not require retraining from scratch, nor access to the data originally used for training. Instead, the weights are modified so that any probing function of the weights is indistinguishable from the same function applied to the weights of a network trained without the data to be forgotten. This condition is a generalized and weaker form of Differential Privacy. Exploiting ideas related to the stability of stochastic gradient descent, we introduce an upper-bound on the amount of information remaining in the weights, which can be estimated efficiently even for deep neural networks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 17 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

AdityaGolatkar/SelectiveForgetting mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from... (arXiv:2003.02960; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified) and The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples (arXiv:2601.22359; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
zero-or-one/URP mentioned on GitHubpytorchMITSyntology: 17 samples, 8 ran (0 instrument-failed) · 9 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran
9unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zero-or-one/URP. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zero-or-one/URP community (archive-listed) 17 samples, 8 ran (0 instrument-failed) · 9 unverified
ConvRes models/models.py ran MIT (permissive) · dad51ff17c8287b6 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-24
class_accuracy learning/learn_utils.py ran fingerprinted MIT (permissive) · 5ec3121ecd2eb357 · report fixture: signature pred_labels:list/1/int, true_labels:list/1/int · returned int · level recorded 2026-09-24
get_param in 15 papers models/models_utils.py ran MIT (permissive) · 16051d5190516416 · report fixture: signature name:str/0/str · returned dict · level recorded 2026-09-24
make_ascent forgetting/forget_utils.py ran fingerprinted MIT (permissive) · f54dac8b9b05da11 · report fixture: signature loss:Tensor/1/float · returned Tensor · level recorded 2026-09-24
model_learning forgetting/forget_utils.py ran MIT (permissive) · 74aea471a48d4f2a · report fixture: signature model:callable/0/?, unfreeze:bool/0/bool · returned Sequential · level recorded 2026-09-24
nip forgetting/forget_utils.py ran fingerprinted MIT (permissive) · fe791ae5d228894f · report fixture: signature v1:ndarray/1/float, v2:ndarray/1/float · returned float64 · level recorded 2026-09-24
regularization in 12 papers learning/learn_utils.py ran MIT (permissive) · 4079cde5d6b5a1af · report fixture: signature model:callable/0/?, lamb:float/0/float, l2:bool/0/bool · returned Tensor · level recorded 2026-09-24
set_loss learning/learn_utils.py ran MIT (permissive) · 09389ab6d25f8096 · report fixture: signature loss:str/0/str, cuda:NoneType/0/? · returned L1Loss · level recorded 2026-09-24
encoder_epoch forgetting/forget.py unverified MIT (permissive) · ee48cdf111bace6c · report
epoch in 23 papers learning/learn.py unverified MIT (permissive) · f8191305d90db998 · report
get_model in 368 papers models/models_utils.py unverified MIT (permissive) · ae937b549e24cb5c · report
get_pdf evaluation/eval_utils.py unverified MIT (permissive) · fe46ceeb9b10981d · report
hiding_helper forgetting/forget.py unverified MIT (permissive) · a286929619f31663 · report
l2_distance in 10 papers evaluation/eval_utils.py unverified MIT (permissive) · 3aec5db3515dd753 · report
predict in 126 papers learning/learn.py unverified MIT (permissive) · b7421427efd627f6 · report
train_encoder forgetting/forget.py unverified MIT (permissive) · 931b41018d2420b8 · report
vectorize_params evaluation/eval_utils.py unverified MIT (permissive) · 15d8d3ae82668ed1 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections