MétaCan
Menu
Back to cohort

Inconspicuous Data Augmentation Based Backdoor Attack on Deep Neural Networks

2022· article· en· W4304140713 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

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
FundersNational Research Foundation SingaporeNational Research FoundationCanadian Institute for Advanced Research
KeywordsBackdoorComputer scienceInterpretabilityArtificial neural networkRobustness (evolution)Artificial intelligenceDeep neural networksEnhanced Data Rates for GSM EvolutionEdge deviceTrojanDeep learningMachine learningComputer securityCloud computingOperating system

Abstract

fetched live from OpenAlex

With new applications made possible by the fusion of edge computing and artificial intelligence (AI) technologies, the global market capitalization of edge AI has risen tremendously in recent years. Deployment of pre-trained deep neural network (DNN) models on edge computing platforms, however, does not alleviate the fundamental trust assurance issue arising from the lack of interpretability of end-to-end DNN solutions. The most notorious threat of DNNs is the backdoor attack. Most backdoor attacks require a relatively large injection rate (≈ 10%) to achieve a high attack success rate. The trigger patterns are not always stealthy and can be easily detected or removed by backdoor detectors. Moreover, these attacks are only tested on DNN models implemented on general-purpose computing platforms. This paper proposes to use data augmentation for backdoor attacks to increase the stealth, attack success rate, and robustness. Different data augmentation techniques are applied independently on three color channels to embed a composite trigger. The data augmentation strength is tuned based on the Gradient Magnitude Similarity Deviation, which is used to objectively assess the visual imperceptibility of the poisoned samples. A rich set of composite triggers can be created for different dirty labels. The proposed attacks are evaluated on pre-activation ResNet18 trained with CIFAR-10 and GTSRB datasets, and EfficientNet-B0 trained with adapted 10-class ImageNet dataset. A high attack success rate of above 97% with only 1% injection rate is achieved on these DNN models implemented on both general-purpose computing platforms and Intel Neural Compute Stick 2 edge AI device. The accuracy loss of the poisoned DNNs on benign inputs is kept below 0.6%. The proposed attack is also tested to be resilient to state-of-the-art backdoor 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 categoriesnone
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 score0.937
Threshold uncertainty score0.732

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0020.002
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

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 head0.058
GPT teacher head0.319
Teacher spread0.260 · 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