MétaCan
Menu
Back to cohort
Record W3153236199 · doi:10.1109/tnnls.2021.3072166

Breaking Neural Reasoning Architectures With Metamorphic Relation-Based Adversarial Examples

2021· article· en· W3153236199 on OpenAlexaff
Alvin Chan, Lei Ma, Felix Juefei-Xu, Yew-Soon Ong, Xiaofei Xie, Minhui Xue, Yang Liu

Bibliographic record

VenueIEEE Transactions on Neural Networks and Learning Systems · 2021
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsAdversarial systemComputer scienceArtificial intelligenceSimple (philosophy)Robustness (evolution)TuringArtificial neural networkScalabilityRelation (database)Focus (optics)Theoretical computer scienceProgramming languageData miningDatabase

Abstract

fetched live from OpenAlex

The ability to read, reason, and infer lies at the heart of neural reasoning architectures. After all, the ability to perform logical reasoning over language remains a coveted goal of Artificial Intelligence. To this end, models such as the Turing-complete differentiable neural computer (DNC) boast of real logical reasoning capabilities, along with the ability to reason beyond simple surface-level matching. In this brief, we propose the first probe into DNC's logical reasoning capabilities with a focus on text-based question answering (QA). More concretely, we propose a conceptually simple but effective adversarial attack based on metamorphic relations. Our proposed adversarial attack reduces DNCs' state-of-the-art accuracy from 100% to 1.5% in the worst case, exposing weaknesses and susceptibilities in modern neural reasoning architectures. We further empirically explore possibilities to defend against such attacks and demonstrate the utility of our adversarial framework as a simple scalable method to improve model adversarial robustness.

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 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)0.014
Version: metacan-v3-hybrid-931329e0061cValidation 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 score0.003
Threshold uncertainty score0.015

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.014
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.003
Scholarly communication0.0010.003
Open science0.0020.004
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0030.001

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 head0.012
GPT teacher head0.223
Teacher spread0.211 · 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 source (direct Gemma or distilled Codex), not a consensus.

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

Citations16
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Neural Networks and Learning SystemsSame topicAdversarial Robustness in Machine LearningFrench-language works237,207