Papers › Delta-Influence: Unlearning Poisons via Influence Functions

Delta-Influence: Unlearning Poisons via Influence Functions

20 Nov 2024arXiv:2411.13731archive 2025-07-28

Wenjie Li, Jiawei Li, Christian Schroeder de Witt, Ameya Prabhu, Amartya Sanyal

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC, often fail to accurately attribute abnormal model behavior to the specific poisoned training data responsible for the data poisoning attack. In addition, traditional unlearning algorithms often struggle to effectively remove the influence of poisoned samples, particularly when only a few affected examples can be identified. To address these challenge, we introduce Δ-Influence, a novel approach that leverages influence functions to trace abnormal model behavior back to the responsible poisoned training data using as little as just one poisoned test example. Δ-Influence applies data transformations that sever the link between poisoned training data and compromised test points without significantly affecting clean data. This allows Δ-Influence to detect large negative shifts in influence scores following data transformations, a phenomenon we term as influence collapse, thereby accurately identifying poisoned training data. Unlearning this subset, e.g. through retraining, effectively eliminates the data poisoning. We validate our method across three vision-based poisoning attacks and three datasets, benchmarking against four detection algorithms and five unlearning strategies. We show that Δ-Influence consistently achieves the best unlearning across all settings, showing the promise of influence functions for corrective unlearning. Our code is publicly available at: https://github.com/andyisokay/delta-influence

PaperPDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 11 samples from 1 repository, 7 ran (4 with no instrument failure; 3 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

andyisokay/delta-influence officialmentioned in paperpytorchSyntology: 1 sample, 0 ran · 1 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.

Code Syntology ran Syntology

12 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
4ran
5unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

andyisokay/delta-influence official repository 1 sample, 0 ran · 1 unverified
_Witch forest/witchcoven/witch_base.py unverified MIT (permissive) · 319676f714a216a9 · report
Ruby-a07/delta-influence found in paper text by Syntology 11 samples, 7 ran (3 instrument-failed) · 4 unverified
average_dicts forest/utils.py ran · our draft was wrong MIT (permissive) · ff0cc040d88bde88 · report fixture: signature running_stats:list/1/dict · returned defaultdict · level recorded 2026-09-25
check_targets forest/victims/training.py ran MIT (permissive) · ccb5c504f069d7e6 · report fixture: signature model:callable/0/?, criterion:callable/0/?, targetset:list/1/tuple, intended_class:list/1/int, original_class:list/1/int, setup:dict/0/? · returned tuple · level recorded 2026-09-25
convnet in 8 papers forest/victims/models.py ran MIT (permissive) · d2f5607b54df5b75 · report fixture: signature width:int/0/int, in_channels:int/0/int, num_classes:int/0/int · returned Sequential · level recorded 2026-09-25
cw_loss in 5 papers forest/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · 6a5967011bf8de7a · report fixture: signature outputs:Tensor/2/float, intended_classes:Tensor/1/int, clamp:int/0/int · returned Tensor · level recorded 2026-09-22
get_optimizers in 7 papers forest/victims/training.py ran MIT (permissive) · 235c22042629630e · report fixture: signature model:callable/0/?, args:dict/0/?, defs:Defs/0/? · returned tuple · level recorded 2026-09-25
linear_model forest/victims/models.py ran · our draft was wrong MIT (permissive) · 0fd172b3dd145268 · report fixture: signature dataset:str/0/str, num_classes:int/0/int · returned Sequential · level recorded 2026-09-25
training_strategy forest/victims/optimization_strategy.py ran MIT (permissive) · e6a7a6941d029556 · report fixture: signature model_name:str/0/str, args:Args/0/? · returned ConservativeStrategy · level recorded 2026-09-25
get_model in 368 papers forest/victims/models.py unverified MIT (permissive) · d180290beeedbcd1 · report
pgd_step forest/victims/utils.py unverified MIT (permissive) · 22091a07a2d0facf · report
run_validation forest/victims/training.py unverified MIT (permissive) · b2c584d7212d6446 · report
system_startup in 5 papers forest/utils.py unverified MIT (permissive) · 120427a416e5f3a1 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for ∆-Influence (graph method: ∆-Influence). 2 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. _Witch entry · level 0 · unverified · 319676f714a216a9
  2. cw_loss helper · level 1 · ran; the contract check could not run (RAISES) · 6a5967011bf8de7a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2411.13731") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AttributeBenchmarkingData Poisoning

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