PaTAS: A Trust Meter for Neural Networks

Kari Jaaskelainen

26 Nov 2025 — 1 min read

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

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A