MétaCan
Menu
Back to cohort

Integrated Sensing and Communications Using Generative AI: Countering Adversarial Machine Learning Attacks

2024· article· en· W4402159627 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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsPolytechnique Montréal
Fundersnot available
KeywordsAdversarial systemGenerative grammarComputer scienceAdversarial machine learningArtificial intelligenceMachine learning

Abstract

fetched live from OpenAlex

In the field of Integrated Sensing and Commu-nication (ISAC) systems, several challenges emerge, such as obtaining the infinitesimal Cramer-Ran lower bound (CRLB) for sensing outcomes and addressing the vulnerabilities of ISAC to adversarial machine learning (AML) attacks. To address this, we propose a Smart ISAC (S-ISAC) system, which incorporates a unique generative adversarial network (GAN) combined with a differentiable Kolmogorov-Smirnov (KS) loss function, named KSGAN. This KSGAN is tailor-made to identify AML attacks on range-Doppler heatmap features. Only after ensuring that the range-Doppler heatmap is free from AML attacks using KSGAN, do we apply the Constant False Alarm Rate (CFAR) for accurate estimation of target vehicle parameters. We implement a rigorous ISAC system under AML attacks using Matlab Toolboxes and the adversarial robustness toolbox (ART). Our numerical findings indicate that the proposed KSGAN offers greater accuracy in detecting AML than a standalone GAN. Additionally, our results show that the MIMO S-ISAC Beamforming surpasses the performance of the standalone ISAC system.

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 score0.650
Threshold uncertainty score0.863

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.001
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 head0.035
GPT teacher head0.316
Teacher spread0.281 · 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