MétaCan
Menu
Back to cohort
Record W4311990442 · doi:10.48550/arxiv.2108.05075

Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks

2021· preprint· en· W4311990442 on OpenAlexfundno aff
Zitao Chen, Pritam Dash, Karthik Pattabiraman

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsAdversarial systemComputer scienceDeep neural networksFalse positive paradoxGenerative grammarBounded functionArtificial intelligenceArtificial neural networkComputer securityMachine learningMathematics

Abstract

fetched live from OpenAlex

Adversarial patch attacks create adversarial examples by injecting arbitrary distortions within a bounded region of the input to fool deep neural networks (DNNs). These attacks are robust (i.e., physically-realizable) and universally malicious, and hence represent a severe security threat to real-world DNN-based systems. We propose Jujutsu, a two-stage technique to detect and mitigate robust and universal adversarial patch attacks. We first observe that adversarial patches are crafted as localized features that yield large influence on the prediction output, and continue to dominate the prediction on any input. Jujutsu leverages this observation for accurate attack detection with low false positives. Patch attacks corrupt only a localized region of the input, while the majority of the input remains unperturbed. Therefore, Jujutsu leverages generative adversarial networks (GAN) to perform localized attack recovery by synthesizing the semantic contents of the input that are corrupted by the attacks, and reconstructs a ``clean'' input for correct prediction. We evaluate Jujutsu on four diverse datasets spanning 8 different DNN models, and find that it achieves superior performance and significantly outperforms four existing defenses. We further evaluate Jujutsu against physical-world attacks, as well as adaptive attacks.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.804
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0040.006
Research integrity0.0010.003
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 head0.047
GPT teacher head0.212
Teacher spread0.166 · 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.

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

Citations1
Published2021
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdversarial Robustness in Machine LearningFrench-language works237,207