Accepted Papers

Advances in Automatically Rating the Trustworthiness of Text Processing Services

Srivastava Biplav (1), Lakkaraju Kausik (1), Bernagozzi Mariana (2), Valtorta Marco (1)

1 - University of South Carolina ( United States), 2 - IBM Research ( United States)

An overview of key trustworthiness attributes and KPIs for trusted ML-based systems engineering

Juliette Mattioli (1), Sohier Henri (2), Delaborde Agnes (2) (3), Amokrane-Ferka Kahina (2), Awadid Afef (2), Chihani Zakaria (4), Khalfaoui Souhaiel (2) (5), Pedroza Gabriel (4)

1 - Thales SA ( France), 2 - IRT SystemX ( France), 3 - LNE ( France), 4 - CEA ( France), 5 - VALEO ( France)

Assessing Systematic Weaknesses of DNNs using Counterfactuals

Gannamaneni Sujan Sai (1), Mock Michael (1), Akila Maram (1)

1 - Fraunhofer IAIS ( Germany)

Conformal Prediction for Trustworthy Detection of Railway Signals

Andéol Léo (1) (2), Fel Thomas (1) (3), Florence De Grancey (4), Mossina Luca (5)

1 - SNCF ( France), 2 - Institut de Mathématiques de Toulouse UMR5219 ( France), 3 - Brown University ( United States), 4 - Thales AVS France ( France), 5 - IRT Saint Exupéry - Institut de Recherche Technologique ( France)

Conformity Assessments under the EU AI Act General Approach

Thelisson Eva (1)

1 - AI Transparency Institute ( Switzerland)

ECS - an Interactive Tool for Data Quality Assurance

Sieberichs Christian (1), Geerkens Simon (1), Braun Alexander (1), Waschulzik Thomas (2)

1 - Hochschule Düsseldorf ( Germany), 2 - Siemens Mobility GmbH ( Germany)

Evaluating Trustworthiness of Decision Tree Learning Algorithms based on Equivalence Checking

Nguena Timo Omer (1), Xiao Tianqi (2), Avellaneda Florent (3), Malik Yasir (4), Bruda Stefan (5)

1 - Université du Québec en Outaouais ( Canada), 2 - Université de Sherbrooke ( Canada), 3 - Université du Québec à Montréal ( Canada), 4 - New York Institute of Technology ( Canada), 5 - Bishop's University ( Canada)

Gender mobility in the labor market with skills-based matching models

Adhikari Ajaya (1), Vethman Steven (1), Vos Daan (1), Lenz Marc (1), Cocu Ioana (1), Tolios Ioannis (1), J. Veenman Cor (1) (2)

1 - The Netherlands Organisation for Applied Scientific Research ( Netherlands), 2 - Leiden University ( Netherlands)

Neighborhood Sampling Confidence Metric for Object Detection

Christophe Gouguenheim (1) (2), Ahmad Berjaoui (2) (3)

1 - Thales Alenia Space [Toulouse] ( France), 2 - IRT SystemX ( France), 3 - IRT Saint Exupéry - Institut de Recherche Technologique ( France)

On the Evaluation of the Symbolic Knowledge Extracted from Black Boxes

Sabbatini Federico (1), Calegari Roberta  (2)

1 - University of Uribino ( Italy), 2 - University of Bologna ( Italy)

Protecting ownership rights of ML models using watermarking in the light of adversarial attacks

Kapusta Katarzyna (1), Lucas Mattioli (2), Addad Boussad (2), Lansari Mohammed (3)

1 - Thales SIX GTS France and IRT System X ( France), 2 - Thales SIX GTS France and IRT SystemX ( France), 3 - Thales SIX GTS ( France)

QI² - an Interactive Tool for Data Quality Assurance

Geerkens Simon (1), Sieberichs Christian (1), Braun Alexander (1), Waschulzik Thomas (2)

1 - Hochschule Düsseldorf ( Germany), 2 - Siemens Mobility GmbH ( Germany)

Real-time Weather Monitoring and Desnowification through Image Purification

Eliott Py (1) , Elies Gherbi(1) , Nelson Fernandez Pinto (1,2), Martin Gonzalez(1) , Hatem Hajri (1)

1 - IRT SystemX ( France), 2 - Air Liquide (France)

Relative Effects of Positive and Negative Explanations on Satisfaction and Performance in Human-Agent Teams

Lavender Bryan (1), Abuhaimed Sami (1), Sen Sandip (1)

1 - Tandy School of Computer Science [Tulsa] ( United States)

Risk Assessment Using Ethical Dimensions

Tartaro Alessio (1), Panai Enrico (1), Cocchiaro Zoe (2)

1 - Università degli Studi di Sassari = University of Sassari [Sassari] ( Italy), 2 - Uniwersytet Jagielloński w Krakowie = Jagiellonian University ( Poland)

To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods

Zhang Dawen (1) (2), Pan Shidong (1) (2), Hoang Thong (1), Xing Zhenchang (1) (2), Staples Mark (1), Xu Xiwei (1), Yao Lina (1), Lu Qinghua (1), Zhu Liming (1)

1 - CSIRO Data61 ( Australia), 2 - Australian National University ( Australia)

Towards a safe MLOps Process for the Continuous Development and Safety Assurance of ML-based Systems in the Railway Domain

Zeller Marc  (1), Waschulzik Thomas (2), Schmid Reiner (1), Bahlmann Claus (2)

1 - Siemens AG ( Germany), 2 - Siemens Mobility GmbH ( Germany)

Using ScrutinAI for Visual Inspection of DNN Performance in a Medical Use Case

Görge Rebekka  (1), Haedecke Elena (1) (2), Mock Michael (1)

1 - Fraunhofer Institute for Intelligent Analysis and Information Systems ( Germany), 2 - University of Bonn, 53113 Bonn, Germany ( Germany)