A Security Verification Framework of Cryptographic Protocols Using Machine Learning

no code implementations • 26 Apr 2023 • Kentaro Ohno, Misato Nakabayashi

We propose a method that allows security verification with computational time on the order of linear with respect to the size of the protocol using machine learning.

Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks

no code implementations • 4 Oct 2022 • Kentaro Ohno, Sekitoshi Kanai, Yasutoshi Ida

We prove that the gradient vanishing of the gate function can be mitigated by accelerating the convergence of the saturating function, i. e., making the output of the function converge to 0 or 1 faster.

Computational Efficiency Time Series +1

One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training

no code implementations • 21 Jul 2022 • Sekitoshi Kanai, Shin'ya Yamaguchi, Masanori Yamada, Hiroshi Takahashi, Kentaro Ohno, Yasutoshi Ida

This paper proposes a new loss function for adversarial training.

Adversarial Robustness

Recurrent Neural Networks for Learning Long-term Temporal Dependencies with Reanalysis of Time Scale Representation

no code implementations • 5 Nov 2021 • Kentaro Ohno, Atsutoshi Kumagai

In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has recently been re-interpreted as a representative of the time scale of the state, i. e., a measure how long the RNN retains information on inputs.