MétaCan
Menu
Back to cohort
Record W4393148616 · doi:10.1609/aaai.v38i5.28228

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

2024· article· en· W4393148616 on OpenAlexafffund
Géraldin Nanfack, Alexander Fulleringer, Jonathan Marty, Michael Eickenberg, Eugene Belilovsky

Bibliographic record

VenueProceedings of the AAAI Conference on Artificial Intelligence · 2024
Typearticle
Languageen
FieldComputer Science
TopicComputational Drug Discovery Methods
Canadian institutionsConcordia UniversityMila - Quebec Artificial Intelligence Institute
FundersFonds de recherche du Québec – Nature et technologies
KeywordsInterpretation (philosophy)MaximizationAdversarial systemComputer scienceArtificial intelligenceComputer securityMathematicsMathematical optimizationProgramming language

Abstract

fetched live from OpenAlex

Feature visualization is one of the most popular techniques used to interpret the internal behavior of individual units of trained deep neural networks. Based on activation maximization, they consist of finding synthetic or natural inputs that maximize neuron activations. This paper introduces an optimization framework that aims to deceive feature visualization through adversarial model manipulation. It consists of finetuning a pre-trained model with a specifically introduced loss that aims to maintain model performance, while also significantly changing feature visualization. We provide evidence of the success of this manipulation on several pre-trained models for the classification task with ImageNet.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.817
Threshold uncertainty score0.425

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.077
GPT teacher head0.326
Teacher spread0.249 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
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

Citations4
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the AAAI Conference on Artificial IntelligenceSame topicComputational Drug Discovery MethodsFrench-language works237,207