cs.DCSep 18, 2026

Trust-Aware Output Management for Physical Neural Network in Cloud-Continuum Systems

Authors: Maliheh Hariri, Stefan Fischer

Organizations: University of Lübeck, Institute of Telematics, 23562 Lübeck, Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Physical Neural Networks (PNNs) introduce new opportunities for cloud continuum computing, but their outputs may be affected by noise, drift, delay, and incomplete reliability information. Existing substrate-management approaches mainly focus on discovery, invocation, and monitoring, while the reliability of the returned output is often left unaddressed. This paper proposes a trust-aware output management framework for heterogeneous PNNs. Each output is represented with quality and context information, and a lightweight edge-level trust score decides whether it should be accepted, rejected, or forwarded to the fog. At the fog layer, compatible outputs are checked for disagreement and combined using reliability- and uncertainty-aware fusion. Historical trust is also tracked to detect sustained degradation and support recalibration requests. The framework is evaluated using controlled and randomized PNN output models. Across 20 random seeds, the proposed full-trust policy reduces unsafe acceptance from approximately 61.5% for raw output handling to about 5.0%, while accepted-output MAE decreases from 0.504 to 0.242. Risk coverage analysis shows that this improvement is not explained only by lower local acceptance. The proposed fog fusion method also achieves the lowest aggregate mean error among the evaluated methods, with a small but consistent advantage over strong uncertainty-aware baselines. The prototype adds about 2 μs2~μ\text{s} of edge processing per evidence record. These results show that post-invocation reliability management can improve the safe use of PNN outputs across edge--fog--cloud systems.

Figures & tables

Research directionEdge/FogUncertaintyFusion/TrustPNN-awarePost-invocation output trust
Physical neural computing and reservoir systems [ 3 , 21 , 13 ]–Partial–✓–
Substrate programming and deployment [ 16 , 25 , 17 , 1 ]Partial––✓–
Wetware access and biological computing [ 10 , 9 , 8 ]Partial––✓–
Edge intelligence [ 19 , 24 , 14 , 2 ]✓––––
Uncertainty-aware edge inference [ 18 ]✓✓–––
Uncertainty-aware sensor fusion and metrology [ 5 , 6 , 22 ]✓✓✓––
Table I: Comparison of the proposed framework with related research directions.
Figure 1: Accepted-output MAE as delay increases. Shorter curves indicate operating regions in which a policy accepts no outputs locally, making accepted-output MAE undefined.
Figure 2: Reliability–coverage trade-off for confidence-only and full-trust selection. CP 2 N 2 is shown as a single accept-all reference point because it has no post-invocation reliability threshold to sweep.
Figure 3: Local acceptance under increasing substrate drift. Full trust progressively shifts uncertain outputs away from local acceptance as degradation becomes stronger.
Figure 4: Local acceptance under increasing physical noise. The full trust policy becomes more selective as output uncertainty increases.
Figure 5: Safety and local availability under increasing physical uncertainty at τ=5\tau=5 s.
Figure 6: Safety and local availability under increasing physical uncertainty at τ=5\tau=5 s.
Figure 7: Accepted-output MAE under increasing noise for the complete trust model and each ablated variant.
Figure 8: False acceptance under increasing substrate drift for the full trust model and its component ablations.
Figure 9: False acceptance under increasing output delay, highlighting the role of freshness in preventing stale-output acceptance.
Figure 10: Mean fusion error as the number of PNN sources increases for the seven evaluated fusion strategies.
Figure 11: Fusion-allowed rate as the number of PNN sources increases under the fixed disagreement threshold.
Figure 12: Adaptive current and historical trust during healthy operation, sustained degradation, and simulated recovery.
Figure 13: Edge-level trust scalability. Total runtime grows approximately proportionally with the number of processed evidence records.
Figure 14: Fog-level processing scalability for numerical fusion and compatibility/disagreement assessment as the number of PNN sources increases.
Figure 16
Figure 17
More in this topic

Physical Neural Networks

See all 10 papers

Explore similar work

CardsList

  1. CP2^2N2^2: A Control Plane for Heterogeneous Physical Neural Networks

    May 5, 2026Stefan Fischer, Maliheh Hariri, Sebastian OtteHeterogeneous ComputingPhysical Neural Networks

    University of Luebeck, Institute of Telematics · University of Luebeck, Institute of Robotics and Cognitive Systems

  2. NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuum

    Mar 22, 2026Peihan Ye, Alfreds Lapkovskis, Alaa Saleh +2Root Cause AnalysisEdge-Cloud Computing

    Department of Computer Systems and Sciences, Stockholm University, Stockholm 164 25, Sweden · Center for Applied Computing, University of Oulu, Oulu 90014, Finland · Computer Science School, Peking University, Beijing 100876, China

  3. PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption

    Jul 20, 2026Sahaj Majavdia, Mahdi TaheriEfficient Neural Network InferenceHomomorphic Encryption

    Brandenburgische Technische Universität Cottbus-Senftenberg, Germany · Humboldt University of Berlin, Germany · Tallinn University of Technology, Tallinn, Estonia