MétaCan
Menu
Back to cohort
Record W4242053016 · doi:10.1109/iccad.2017.8203770

Fault injection attack on deep neural network

2017· article· en· W4242053016 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

Venue2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) · 2017
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
FundersGuangdong Academy of SciencesNational Natural Science Foundation of ChinaCanadian Institute for Advanced Research
KeywordsFault injectionArtificial neural networkComputer scienceFault (geology)Set (abstract data type)Gradient descentDeep neural networksArtificial intelligenceDescent (aeronautics)Class (philosophy)Control theory (sociology)Engineering

Abstract

fetched live from OpenAlex

Deep neural network (DNN), being able to effectively learn from a training set and provide highly accurate classification results, has become the de-facto technique used in many mission-critical systems. The security of DNN itself is therefore of great concern. In this paper, we investigate the impact of fault injection attacks on DNN, wherein attackers try to misclassify a specified input pattern into an adversarial class by modifying the parameters used in DNN via fault injection. We propose two kinds of fault injection attacks to achieve this objective. Without considering stealthiness of the attack, single bias attack (SBA) only requires to modify one parameter in DNN for misclassification, based on the observation that the outputs of DNN may linearly depend on some parameters. Gradient descent attack (GDA) takes stealthiness into consideration. By controlling the amount of modification to DNN parameters, GDA is able to minimize the fault injection impact on input patterns other than the specified one. Experimental results demonstrate the effectiveness and efficiency of the proposed 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.

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 categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication, Open science, Insufficient payload (model declined to judge)
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 score0.853
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0020.002
Open science0.0080.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.001

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 head0.162
GPT teacher head0.363
Teacher spread0.202 · 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