MétaCan
Menu
Back to cohort
Record W4206060246 · doi:10.1109/access.2021.3133334

You Can’t Fool All the Models: Detect Adversarial Samples via Pruning Models

2021· article· en· W4206060246 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueIEEE Access · 2021
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
FundersNatural Science Foundation of Zhejiang ProvinceNational Natural Science Foundation of ChinaCanadian Institute for Advanced Research
KeywordsComputer scienceAdversarial systemPruningArtificial intelligenceMachine learningDeep neural networksArtificial neural networkFLOPSDeep learningSample (material)Pattern recognition (psychology)

Abstract

fetched live from OpenAlex

Many adversarial attack methods have investigated the security issue of deep learning models. Previous works on detecting adversarial samples show superior in accuracy but consume too much memory and computing resources. In this paper, we propose an adversarial sample detection method based on pruned models and evaluate four different pruning methods. We find that pruned neural network models are sensitive to adversarial samples, i.e., the pruned models tend to output labels different from the original model when given adversarial samples. Moreover, the pruned model has an extremely small model size and computational cost. Based on the detection result, we further propose a simple but effective defense approach to identify the true label of the adversarial sample. Experiments show that, on average, four different pruning methods outperform the SOTA multi-model based detection method (64.15% and 73.70%) by 28.65% and 18.73% on CIFAR10 and SVHN, respectively, with significantly fewer models used. The FLOPs of our structured pruned model are only 49.41% and 25.62% of the original model. Our defense approach achieves 68.60% and 72.03% average classification accuracy on CIFAR10 and SVHN, exceeding other advanced defense methods.

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.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.944
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.003
Open science0.0040.001
Research integrity0.0000.001
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 head0.307
Teacher spread0.230 · 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