MétaCan
Menu
Back to cohort
Record W4292971553 · doi:10.1109/tdsc.2022.3200421

Self-Checking Deep Neural Networks for Anomalies and Adversaries in Deployment

2022· article· en· W4292971553 on OpenAlex
Yan Xiao, Ivan Beschastnikh, Yun Lin, Rajdeep Singh Hundal, Xiaofei Xie, David S. Rosenblum, Jin Song Dong

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueIEEE Transactions on Dependable and Secure Computing · 2022
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of British Columbia
FundersNatural Sciences and Engineering Research Council of CanadaBộ Giáo dục và Ðào tạoNational Research FoundationMinistry of Education - SingaporeNational Research Foundation SingaporeNational University of SingaporeCisco Systems
KeywordsComputer scienceAdversarial systemSoftware deploymentArtificial neural networkArtificial intelligenceDeep neural networksFalse alarmConstant false alarm rateMachine learningDomain (mathematical analysis)Margin (machine learning)SoftwareData miningSoftware engineering

Abstract

fetched live from OpenAlex

Deep Neural Networks (DNNs) have been widely adopted, yet DNN models are surprisingly unreliable, which raises significant concerns about their use in critical domains. In this work, we propose that runtime DNN mistakes can be quickly detected and properly dealt with <i>in deployment</i>, especially in settings like self-driving vehicles. Just as software engineering (SE) community has developed effective mechanisms and techniques to monitor and check programmed components, our previous work, SelfChecker, is designed to monitor and correct DNN predictions given unintended abnormal test data. SelfChecker triggers an alarm if the decisions given by the internal layer features of the model are inconsistent with the final prediction and provides <i>advice</i> in the form of an alternative prediction. In this paper, we extend SelfChecker to the security domain. Specifically, we describe SelfChecker++, which we designed to target both <i>unintended</i> abnormal test data and <i>intended</i> adversarial samples. Technically, we develop a technique which can transform any runtime inputs triggering alarms into semantically equivalent inputs, then we feed those transformed inputs to the model. Such runtime transformation nullifies any intended crafted samples, making the model immune to adversarial attacks that craft adversarial samples. We evaluated the alarm accuracy of SelfChecker++ on three DNN models and four popular image datasets, and found that SelfChecker++ triggers correct alarms on 63.10% of wrong DNN predictions, and triggers false alarms on 5.77% of correct DNN predictions. We also evaluated the effectiveness of SelfChecker++ in detecting adversarial examples and found it detects on average 70.09% of such samples with advice accuracy that is 20.89% higher than the original DNN model and 18.37% higher than SelfChecker.

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)0.000
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: Empirical · Consensus signal: none
Teacher disagreement score0.885
Threshold uncertainty score0.951

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
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 head0.010
GPT teacher head0.235
Teacher spread0.225 · 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