MétaCan
Menu
Back to cohort
Record W4415057288 · doi:10.48550/arxiv.2509.06896

Are Targeted Data Poisoning Attacks as Effective as We Think?

2025· preprint· en· W4415057288 on OpenAlexfundno aff
Weina Xu, Yiwei Lu, Yihan Wang, Matthew Y. R. Yang, Zuoqiu Liu, Gautam Kamath, Yaoliang Yu

Bibliographic record

VenueArXiv.org · 2025
Typepreprint
Languageen
FieldComputer Science
TopicComputational Drug Discovery Methods
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaGovernment of CanadaCanadian Institute for Advanced Research
KeywordsVulnerability (computing)Test (biology)Sample (material)Key (lock)Poison control

Abstract

fetched live from OpenAlex

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true worst-case effectiveness. We argue that the right evaluation focuses on the hardest samples to poison. The same reasoning applies to defense: since targeted attacks leave no footprint at the distribution level, defenders should proactively identify the most vulnerable samples and apply targeted countermeasures. Given a test dataset, this paper identifies both the easiest and hardest to poison examples based on only clean model information. Specifically, we offer coarse evaluations using clean training dynamics, and fine-grained classification on poison class using poison distances and budgets. Our experiments show these metrics reliably stratify samples by poisoning vulnerability, enabling both rigorous worst-case evaluation and proactive vulnerability-aware defense.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.018
metaresearch head score (Gemma)0.082
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.018
Threshold uncertainty score0.094

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0180.082
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0010.005
Scholarly communication0.0060.012
Open science0.0020.003
Research integrity0.0050.004
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.086
GPT teacher head0.384
Teacher spread0.298 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueArXiv.orgSame topicComputational Drug Discovery MethodsFrench-language works237,207