Protecting ownership rights of ML models using watermarking in the light of adversarial attacks
Authors (first, second and last of 4)
Collection
AI Trustworthiness Evaluation
AAAI Spring Symposium 2023 - This symposium aims to explore innovative approaches, metrics and/or methods proposed by academia or industry, to ”assess the trust and trustworthiness” of AI-based critical systems.
The AI Transparency Institute and Confiance AI, Guest Editors of this Special Collection are pleased to share the result of the AAAI Spring Symposium 2023 with you.
Editors
-
Bertrand Braunschweig
Bertrand Braunschweig, Coordonnateur scientifique du programme confiance.ai, confiance.ai, Palaiseau, France, bertrand.braunschweig@irt-systemx.fr
-
Juliette Mattioli
Juliette Mattioli, Thales Group, Paris, France, Juliette.mattioli@thalesgroup.com
-
Eva Thelisson
Eva Thelisson, AI Transparency Institute, Lausanne, Switzerland, eva@aitransparencyinstitute.com
Articles (19 in this collection)
-
-
Evaluating trustworthiness of decision tree learning algorithms based on equivalence checking
Authors (first, second and last of 5)
-
Real-time weather monitoring and desnowification through image purification
Authors (first, second and last of 5)
-
Conformal prediction for trustworthy detection of railway signals
Authors (first, second and last of 4)
-
-
Gender mobility in the labor market with skills-based matching models
Authors (first, second and last of 7)
-
-
An overview of key trustworthiness attributes and KPIs for trusted ML-based systems engineering
Authors (first, second and last of 8)
-
-
-
-
Toward a safe MLOps process for the continuous development and safety assurance of ML-based systems in the railway domain
Authors (first, second and last of 4)
-
-
-
-
To be forgotten or to be fair: unveiling fairness implications of machine unlearning methods
Authors (first, second and last of 9)
-
-
-
Advances in automatically rating the trustworthiness of text processing services
Authors (first, second and last of 4)
