SENA: Similarity-based Error-checking of Neural Activations - Espace pour le Développement Access content directly
Conference Papers Year : 2023

SENA: Similarity-based Error-checking of Neural Activations


In this work, we propose SENA, a run-time monitor focused on detecting unreliable predictions from machine learning (ML) classifiers. The main idea is that instead of trying to detect when an image is out-of-distribution (OOD), which will not always result in a wrong output, we focus on detecting if the prediction from the ML model is not reliable, which will most of the time result in a wrong output, independently of whether it is in-distribution (ID) or OOD. The verification is done by checking the similarity between the neural activations of an incoming input and a set of representative neural activations recorded during training. SENA uses information from true-positive and false-negative examples collected during training to verify if a prediction is reliable or not. Our approach achieves results comparable to state-of-the-art solutions without requiring any prior OOD information and without hyperparameter tuning. Besides, the code is publicly available for easy reproducibility at
Fichier principal
Vignette du fichier
ECAI.pdf (578.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04212952 , version 1 (20-09-2023)


  • HAL Id : hal-04212952 , version 1


Raul Sena Ferreira, Joris Guerin, Jeremie Guiochet, Hélène Waeselynck. SENA: Similarity-based Error-checking of Neural Activations. 27th European Conference on Artificial Intelligence - ECAI 2023, Sep 2023, Krakow, Poland. ⟨hal-04212952⟩
23 View
11 Download


Gmail Facebook X LinkedIn More