Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IBISML, IPSJ-CVIM |
2024-03-04 09:12 |
Hiroshima |
Hiroshima Univ. Higashi-Hiroshima campus (Primary: On-site, Secondary: Online) |
Creating Adversarial Examples to Deceive Both Humans and Machine Learning Models Ko Fujimori (Waseda Univ.), Toshiki Shibahara (NTT), Daiki Chiba (NTT Security), Mitsuaki Akiyama (NTT), Masato Uchida (Waseda Univ.) PRMU2023-65 |
One of the vulnerability attacks against neural networks is the generation of Adversarial Examples (AE), which induce mi... [more] |
PRMU2023-65 pp.82-87 |
SIP, IT, RCS |
2024-01-19 13:30 |
Miyagi |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
Problem of Adversarial Attacks on CNN-based Image Classifiers and Countermeasures Minoru Kuribayashi (Tohoku Univ.) IT2023-67 SIP2023-100 RCS2023-242 |
It is well-known that discriminative models based on deep learning techniques may cause misclassification if adversarial... [more] |
IT2023-67 SIP2023-100 RCS2023-242 p.204 |
EMM |
2024-01-17 10:55 |
Miyagi |
Tohoku Univ. (Primary: On-site, Secondary: Online) |
Detecting Adversarial Examples using Filtering Operation Based on JPEG-Compression-Derived Distortion Kenta Tsunomori (Okayama Univ.), Minoru Kuribayashi (Tohoku Univ.), Nobuo Funabiki (Okayama Univ.) EMM2023-87 |
Image classifiers based on convolutional neural networks are caused misclassification by adversarial perturbations. In t... [more] |
EMM2023-87 pp.38-43 |
IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2023-02-21 11:10 |
Hokkaido |
Hokkaido Univ. |
[Special Talk]
Study of Probability Modeling for Lossless Image Coding Using Example Search and Adaptive Prediction Hiroki Kojima (KDDI), Yasuyo Kita, Ichiro Matsuda (Tokyo Univ. of Science) ITS2022-46 IE2022-63 |
Many efficient lossless image coding methods predict the next pel value to be coded from the pels already coded, and rem... [more] |
ITS2022-46 IE2022-63 p.25 |
HWS, ICD |
2022-10-25 13:50 |
Shiga |
(Primary: On-site, Secondary: Online) |
Fundamental Study of Adversarial Examples Created by Fault Injection Attack on Image Sensor Interface Tatsuya Oyama, Kota Yoshida, Shunsuke Okura, Takeshi Fujino (Ritsumeikan Univ.) HWS2022-36 ICD2022-28 |
Adversarial examples (AEs), which cause misclassification by adding subtle perturbations to input images, have been prop... [more] |
HWS2022-36 ICD2022-28 pp.35-40 |
PRMU, IPSJ-CVIM |
2022-03-10 17:30 |
Online |
Online |
Adversarial Training: A Survey Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi (Chubu Univ.) PRMU2021-73 |
Adversarial training (AT) is a training method that aims to obtain a robust model for defencing the adversarial attack b... [more] |
PRMU2021-73 pp.78-90 |
PRMU |
2021-10-09 09:30 |
Online |
Online |
Explaining Adversarial Examples by the Embedding Structure of Data Manifold Hajime Tasaki, Yuji Kaneko, Jinhui Chao (Chuo Univ.) PRMU2021-19 |
It is widely known that adversarial examples cause misclassification in classifiers using deep learning. Inspite of nume... [more] |
PRMU2021-19 pp.17-21 |
IE, SIP, BioX, ITE-IST, ITE-ME [detail] |
2021-06-03 16:00 |
Online |
Online |
Fast Implementation of the Lossless Image Coding Method Based on Example Search and Probability Model Optimization Hiroki Kojima, Yusuke Kameda, Yasuyo Kita, Ichiro Matsuda, Susumu Itoh (Tokyo Univ of Science.) SIP2021-3 BioX2021-3 IE2021-3 |
We previously proposed a lossless image coding method based on example search and probability model optimization. In the... [more] |
SIP2021-3 BioX2021-3 IE2021-3 pp.10-14 |
EMM |
2021-03-04 14:15 |
Online |
Online |
[Poster Presentation]
Detection of Adversarial Examples in CNN Image Classifiers Using Features Extracted with Multiple Strengths of Filter Akinori Higashi, Minoru Kuribayashi, Nobuo Funabiki (Okayama Univ.), Huy Hong Nguyen, Isao Echizen (NII) EMM2020-70 |
Deep learning has been used as a new method for machine learning, and its performance has been significantly improved. A... [more] |
EMM2020-70 pp.19-24 |
ICSS, IPSJ-SPT |
2021-03-02 13:40 |
Online |
Online |
Research on the vulnerability of homoglyph attacks to online machine translation system Takeshi Sakamoto, Tatsuya Mori (Waseda Univ) ICSS2020-50 |
It has been widely known that systems empowered by neural network algorithms are vulnerable against an intrinsic attack ... [more] |
ICSS2020-50 pp.144-149 |
IE |
2021-01-21 14:00 |
Online |
Online |
[Invited Talk]
Lossless Image/Video Coding Method Based on Probability Model Estimation and Optimization Kyohei Unno (KDDI Research) IE2020-36 |
In this talk, the lossless image/video coding method that is proposed by the author is introduced. The proposed method e... [more] |
IE2020-36 p.8 |
COMP, IPSJ-AL |
2020-05-09 09:30 |
Online |
Online |
On Power and limitation of adversarial example attacks Kouichi Sakurai (Kyushu Univ.) COMP2020-5 |
A risk of adversarial example attacks which cause deep learning to make wrong decisions is getting serious even from a c... [more] |
COMP2020-5 pp.33-36 |
ICSS, IPSJ-SPT |
2020-03-03 11:40 |
Okinawa |
Okinawa-Ken-Seinen-Kaikan (Cancelled but technical report was issued) |
Adversarial Attacks against Electrocardiograms Taiga Ono (Waseda Univ.), Takeshi Sugawara (UEC), Tatsuya Mori (Waseda Univ.) ICSS2019-90 |
Recent advancements in clinical services powered by deep learning have been met with the threat of Adversarial Examples.... [more] |
ICSS2019-90 pp.131-136 |
SSS |
2019-09-24 15:15 |
Tokyo |
|
A Proposal of Detection Method of Adversalial Examples based on Frequency Domain Yuya Kase, Masaomi Kimura (SIT) SSS2019-20 |
We propose a detection method of special data Adversarial Examples that cause misclassification of neural networks. Adve... [more] |
SSS2019-20 pp.13-16 |
EMM, IT |
2019-05-23 16:35 |
Hokkaido |
Asahikawa International Conference Hall |
[Invited Talk]
Security of Machine Learning Satsuya Ohata (AIST), Yuya Senzaki (Idein) IT2019-6 EMM2019-6 |
In this talk, we introduce several research results on machine learning security. Especially, we will explain about adve... [more] |
IT2019-6 EMM2019-6 p.29 |
EMM |
2019-03-13 16:25 |
Okinawa |
TBD |
Improving the robusteness of neural networks to adversarial examples by reducing color depth of training inage data Shuntaro Miyazato, Toshihiko Yamasaki, Kiyoharu Aizawa (UTokyo) EMM2018-109 |
In this research, we propose a method to train a neural network that is robust to adversarial examples to image classifi... [more] |
EMM2018-109 pp.95-100 |
ET |
2018-06-16 14:00 |
Aichi |
Nanzan University |
Database of Examples of Data File for Exercises on Data Analysis Katsumi Yoshine (Nanzan Univ.) ET2018-14 |
The class concerning data analysis consists of lecture and exercises. In the lecture, a statistical theory is taught. In... [more] |
ET2018-14 pp.13-16 |
SS, KBSE, IPSJ-SE [detail] |
2017-07-19 17:50 |
Hokkaido |
|
Framework for interactive characterization and annotation of part of source code Ken Nakayama (Tsuda Univ.), Shun'ichi Tano, Tomonori Hashiyama (UEC) SS2017-15 KBSE2017-15 |
Identifying and presenting semantic chunks or relations in source code will help source code comprehension by an enginee... [more] |
SS2017-15 KBSE2017-15 pp.85-90 |
SP, SIP, EA |
2017-03-01 16:40 |
Okinawa |
Okinawa Industry Support Center |
[Invited Talk]
An Introduction to Example-based Speech Enhancement and Its Improvements Atsunori Ogawa, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani (NTT) EA2016-114 SIP2016-169 SP2016-109 |
This paper introduces example-based speech enhancement, which is a promising single-channel approach to cope with highly... [more] |
EA2016-114 SIP2016-169 SP2016-109 pp.183-188 |
ET |
2016-03-05 11:10 |
Kagawa |
Kawaga Univ. (Saiwai-cho Campus) |
Co-Occurrence Corpus Based on Parsing of Phrase Structure and Dependency Structure for Second Language Writing Hou Riku, Yasuo Miyoshi (Kochi Univ.) ET2015-114 |
In this research, the example sentences that match the intended want to tell at the time of the second language writing ... [more] |
ET2015-114 pp.115-118 |