Search Results for author: Toshihiro Matsui

Found 6 papers, 0 papers with code

Search Space of Adversarial Perturbations against Image Filters

no code implementations5 Mar 2020 Dang Duy Thang, Toshihiro Matsui

Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to deceive the deep learning system.

Adversarial Attack Image Classification

Automated Detection System for Adversarial Examples with High-Frequency Noises Sieve

no code implementations5 Aug 2019 Dang Duy Thang, Toshihiro Matsui

Deep neural networks are being applied in many tasks with encouraging results, and have often reached human-level performance.

Image Transformation can make Neural Networks more robust against Adversarial Examples

no code implementations10 Jan 2019 Dang Duy Thang, Toshihiro Matsui

We found giving a rotation to an adversarial example image can defeat the effect of adversarial examples.

Utilitarian Distributed Constraint Optimization Problems

no code implementations22 Apr 2016 Julien Savaux, Julien Vion, Sylvain Piechowiak, René Mandiau, Toshihiro Matsui, Katsutoshi Hirayama, Makoto Yokoo, Shakre Elmane, Marius Silaghi

The Distributed Constraint Optimization Problem (DCOP) is a fundamental model used to approach various families of distributed problems.

DisCSPs with Privacy Recast as Planning Problems for Utility-based Agents

no code implementations22 Apr 2016 Julien Savaux, Julien Vion, Sylvain Piechowiak, René Mandiau, Toshihiro Matsui, Katsutoshi Hirayama, Makoto Yokoo, Shakre Elmane, Marius Silaghi

In these extensions we assume that the planning problem is further restricting the set of communication actions to only the communication primitives present in the corresponding solver protocols.

Cannot find the paper you are looking for? You can Submit a new open access paper.