Get Started
Home
Topics
Search
Library
Research questionHow can learned cell-free ISAC schedulers produce feasible decisions from potentially false AP statistics?Learned schedulers can achieve high prediction scores while still violating joint association and scheduling constraints. False reports from one AP can further increase infeasibility, particularly when the falsified statistics affect constraints rather than only the objective.
AI
Evaluation & Benchmarks
Machine Learning
Multi-agent Systems
Neural and Evolutionary Computing
Technology
Latest papersRecent research connected to this question, newest first.Feasible but Not Safe: Constraint Violations and Report-Channel Attacks in Learned Cell-Free ISAC AssociationThe source concerns a graph-neural-network scheduler that uses lightweight per-AP statistics to select AP clustering, user and target scheduling, and operating modes. Its evidence covers feasibility projection, false-data injection by a single malicious AP, and cross-AP consistency checks; it does not establish broader attack or deployment guarantees.research paper · Sep 2, 2026
Related questions
How can automated travel planners generate itineraries that withstand transit delays and crowd variability?How can intelligent systems be compared under deployment constraints when representational economy, prediction, and resource use trade off?How can human-AI teams avoid failure when AI is fast but error-prone or slow but accurate?How should dependent LLM inference tasks be coordinated across edge servers when deadlines allow only limited extensions?