MétaCan
Menu
Back to cohort
Record W4288391571 · doi:10.1109/tse.2022.3194640

FalsifAI: Falsification of AI-Enabled Hybrid Control Systems Guided by Time-Aware Coverage Criteria

2022· article· en· W4288391571 on OpenAlexaff
Zhenya Zhang, Deyun Lyu, Paolo Arcaini, Lei Ma, Ichiro Hasuo, Jianjun Zhao

Bibliographic record

VenueIEEE Transactions on Software Engineering · 2022
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsComputer scienceCorrectnessRobustness (evolution)Artificial neural networkNotationContext (archaeology)Hybrid systemSemantics (computer science)Artificial intelligenceModel checkingTheoretical computer scienceProgramming languageMachine learning

Abstract

fetched live from OpenAlex

Modern Cyber-Physical Systems (CPSs) that need to perform complex control tasks (e.g., autonomous driving) are increasingly using AI-enabled controllers, mainly based on deep neural networks (DNNs). The quality assurance of such types of systems is of vital importance. However, their verification can be extremely challenging, due to their complexity and uninterpretable decision logic. Falsification is an established approach for CPS quality assurance, which, instead of attempting to prove the system correctness, aims at finding a time-variant input signal violating a formal specification describing the desired behavior; it often employs a search-based testing approach that tries to minimize therobustnessof the specification, given by its quantitative semantics. However, guidance provided by robustness is mostly black-box and only related to the system output, but does not allow to understand whether the temporal internal behavior determined by multiple consecutive executions of the neural network controller has been explored sufficiently. To bridge this gap, in this paper, we make an early attempt at exploring the temporal behavior determined by the repeated executions of the neural network controllers in hybrid control systems and first propose eight time-aware coverage criteria specifically designed for neural network controllers in the context of CPS, which consider different features by design: the simple temporal activation of a neuron, the continuous activation of a neuron for a given duration, and the differential neuron activation behavior over time. Second, we introduce a falsification framework, named$\mathtt {FalsifAI}$, that exploits the coverage information for better falsification guidance. Namely, inputs of the controller that increase the coverage (so improving theexplorationof the DNN behaviors), are prioritized in theexploitationphase of robustness minimization. Our large-scale evaluation over a total of 3 typical CPS tasks, 6 system specifications, 18 DNN models and more than 12,000 experiment runs, demonstrates 1) the advantage of our proposed technique in outperforming two state-of-the-art falsification approaches, and 2) the usefulness of our proposed time-aware coverage criteria for effective falsification guidance.

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

Direct model labels (unvalidated)

Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.

Model armCategoriesStudy designConfidence
gemmano category
Domain: not available · Genre: Methods
About the Canadian research system: no · About a Canadian topic: no
Not applicablelow
gptno category
Domain: not available · Genre: Software
About the Canadian research system: no · About a Canadian topic: no
Other designhigh
models splitAgreement compares identical category sets and study designs across arms.

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.017
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.017

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.017
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0010.000
Science and technology studies0.0010.003
Scholarly communication0.0020.002
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.000

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 head0.008
GPT teacher head0.226
Teacher spread0.218 · 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

Labeled directly by 2 models reading the full record.

The models applied no category: nothing in the taxonomy fit this work.

The models disagree on parts of this classification; every voice is preserved in the section at the end of the page.

Study designNot applicable · Other design
Domainnot available
GenreMethods · Software

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

Citations24
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Software EngineeringSame topicAdversarial Robustness in Machine LearningFrench-language works237,207