# PaTAS: A Framework for Trust Propagation in Neural Networks Using Subjective Logic

arXiv: https://arxiv.org/abs/2511.20586 · HTML: https://mlsanity.com/paper/2511.20586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 60 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Dos and Don'ts of Machine Learning in Computer Security](https://mlsanity.com/paper/2010.09470/) (2020)
- [From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered](https://mlsanity.com/paper/2506.07461/) (2025)
- [Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images](https://mlsanity.com/paper/2508.00549/) (2025)
- [Establishing and Evaluating Trustworthy AI: Overview and Research Challenges](https://mlsanity.com/paper/2411.09973/) (2024)
- [Multi-Source Fusion Operations in Subjective Logic](https://mlsanity.com/paper/1805.01388/) (2018)
- [Quantifying Calibration Error in Neural Networks Through Evidence-Based Theory](https://mlsanity.com/paper/2411.00265/) (2024)
- [Trustworthy Transfer Learning: A Survey](https://mlsanity.com/paper/2412.14116/) (2024)
- [Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias](https://mlsanity.com/paper/2508.13813/) (2025)

## Abstract (arXiv)

Trustworthiness has become a key requirement for deploying artificial intelligence in safety-critical applications, yet conventional metrics such as accuracy fail to capture uncertainty or the reliability of predictions, particularly under adversarial or degraded conditions. This paper introduces the Parallel Trust Assessment System (PaTAS), a framework for modeling and propagating trust in neural networks using Subjective Logic (SL). PaTAS operates in parallel with standard neural computation through Trust Nodes and Trust Functions that propagate input, parameter, and activation trust across the network, refining parameter trust during training (Parameter Trust Update) and returning a per-inference trust opinion, quantifying belief, disbelief, and uncertainty, on each prediction (Inference-Path Trust Assessment). Experiments on real-world and adversarial datasets show that these estimates are interpretable and stable and complement accuracy: PaTAS flags predictions that remain accurate yet rely on parameters learned from corrupted data, detects adversarially patched inputs without knowledge of the trigger, and audits training-label corruption without any test data. Compared with output-only uncertainty baselines and dedicated input- and feature-space detectors, out-of-distribution and corruption detection is carried by the conformity-derived input opinions PaTAS consumes, within a regime that a per-dataset diagnostic identifies in advance; trust propagation adds model-side signals these detectors lack, and the composed trust degrades gracefully where any single signal fails. The mechanism extends to convolutional networks. PaTAS thereby provides a foundation for transparent, quantifiable trust reasoning across the AI lifecycle.