PaTAS: A Trust Meter for Neural Networks
AI used in healthcare, cars, and finance must be trustworthy. Accuracy alone can’t show when a model is unsure or under attack.
Meet PaTAS — a parallel "trust meter" for neural networks built on Subjective Logic.
- Runs alongside normal model math with special Trust Nodes and Trust Functions.
- Tracks trust in inputs, parameters, and activations as data flows through the network.
- Updates parameter reliability during training.
- At inference, computes a case-by-case trust score (IPTA) for each prediction.
In tests on real and adversarial datasets, PaTAS separated benign from malicious inputs and exposed gaps where model confidence didn’t match reality—delivering interpretable, stable trust estimates that complement accuracy.
Bottom line: PaTAS brings transparent, quantifiable trust to the full AI lifecycle—supporting safer deployment, better monitoring, and clearer audits.
Paper by K. I. Ouattara, I. Krontiris, T. Dimitrakos, D. Eisermann, F. Kargl. Read: https://arxiv.org/abs/2511.20586v1
Paper: https://arxiv.org/abs/2511.20586v1
Register: https://www.AiFeta.com
#AI #TrustworthyAI #MachineLearning #NeuralNetworks #AdversarialRobustness #Safety #SubjectiveLogic #XAI
