MétaCan
Menu
Back to cohort
Record W6987051597

Security by Design: Reducing Information Exchange in Multi-Agent Search Tasks

2021· dissertation· en· W6987051597 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

VenueQSpace (Queen's University Library) · 2021
Typedissertation
Languageen
FieldComputer Science
TopicDistributed Control Multi-Agent Systems
Canadian institutionsQueen's University
Fundersnot available
KeywordsTask (project management)Information exchangeExploitDependency (UML)Information systemAdversarial systemTask analysisMulti-agent systemInformation structure
DOInot available

Abstract

fetched live from OpenAlex

Intrinsic to multi-agent systems is the trait of inter-agent dependency on information exchange. During safety-critical tasks, errors in information exchange between agents can lead to vulnerable system behaviour. Consequently, adversarial agents often seek to exploit this vulnerability, rather than exploiting the communicated information itself. Motivated by this problem, the objective of this research is to investigate alternative coordination strategies of multi-agent systems that reduce information exchange and maximize task efficiency.
\n
\nWe consider the task of a multi-agent system of autonomous agents, such as a team of vehicles, performing a reconnaissance mission in an unknown, hostile, and urban environment. We abstract this task by considering a two-agent system exploring an unknown and structured maze. The goal of the agents is to search all states in the maze while minimizing communication and maximizing search efficiency.
\n
\nOur results demonstrate that through restricting communication to line-of-sight, exploiting the structure of the environment, and employing deterministic decision-making policies, information exchange can be reduced while preserving a high degree of efficiency in the coordination of autonomous agents.

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 categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.829
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0010.007
Open science0.0020.001
Research integrity0.0010.001
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 head0.015
GPT teacher head0.218
Teacher spread0.203 · 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