no code implementations • 18 Jan 2023 • Yusuke Kawamoto, Kazumasa Miyake, Koichi Konishi, Yutaka Oiwa
In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems.
no code implementations • 30 Oct 2022 • Yusuke Kawamoto, Tetsuya Sato, Kohei Suenaga
We propose a formal language for describing and explaining statistical causality.
no code implementations • 15 Aug 2022 • Yusuke Kawamoto, Tetsuya Sato, Kohei Suenaga
We propose a new approach to formally describing the requirement for statistical inference and checking whether a program uses the statistical method appropriately.
no code implementations • 30 May 2022 • Ryuta Arisaka, Ryoma Nakai, Yusuke Kawamoto, Takayuki Ito
We present core formal constraints for the theme aspect argumentation model and then more formal constraints that improve its fallacy identification capability.
no code implementations • 22 Dec 2020 • Mário S. Alvim, Konstantinos Chatzikokolakis, Yusuke Kawamoto, Catuscia Palamidessi
A common goal in the areas of secure information flow and privacy is to build effective defenses against unwanted leakage of information.
no code implementations • 30 Nov 2020 • Seira Hidano, Takao Murakami, Yusuke Kawamoto
Transfer learning has been widely studied and gained increasing popularity to improve the accuracy of machine learning models by transferring some knowledge acquired in different training.
no code implementations • 19 Oct 2020 • Natasha Fernandes, Yusuke Kawamoto, Takao Murakami
Then we show that our mechanisms enable friend matching with high utility and rigorous privacy guarantees based on extended DP.
no code implementations • 27 Apr 2020 • Yusuke Kawamoto
We propose an epistemic approach to formalizing statistical properties of machine learning.
1 code implementation • 11 Nov 2019 • Takao Murakami, Koki Hamada, Yusuke Kawamoto, Takuma Hatano
We model various statistical features of the original traces by a transition-count tensor and a visit-count tensor.
no code implementations • 24 Jul 2019 • Yusuke Kawamoto
Specifically, we propose a formal model for statistical classification based on a Kripke model, and formalize various notions of classification performance, robustness, and fairness of classifiers by using epistemic logic.
no code implementations • 13 Jul 2019 • Yusuke Kawamoto, Takao Murakami
We introduce a general model for the local obfuscation of probability distributions by probabilistic perturbation, e. g., by adding differentially private noise, and investigate its theoretical properties.
no code implementations • 3 Dec 2018 • Yusuke Kawamoto, Takao Murakami
To improve the tradeoff between distribution privacy and utility, we introduce a local obfuscation mechanism, called a tupling mechanism, that adds random dummy data to the output.
Cryptography and Security Databases Information Theory Information Theory
no code implementations • 23 Jul 2018 • Yusuke Kawamoto, Takao Murakami
Obfuscation techniques in location-based services (LBSs) have been shown useful to hide the concrete locations of service users, whereas they do not necessarily provide the anonymity.
Cryptography and Security Databases Information Theory Information Theory