Financial News
Fujitsu, Toyo University, and Amagasaki City leverage AI technology and psychological research in trial to protect senior citizens from phone fraud
By:
Fujitsu Ltd via
ACN Newswire
March 24, 2022 at 05:08 AM EDT
TOKYO, Mar 24, 2022 - (JCN Newswire) - Fujitsu, Toyo University Incorporated Educational Institution (Toyo University), and Amagasaki City(1) announced the launch of Japan's first joint research project leveraging converging technologies(2) that combine AI techniques and psychological research into the emotional state of victims of phone fraud and other scams. The objective of the joint research will be the development of an AI model capable of detecting various types of phone fraud(3), contributing to the prevention of scams that target senior citizens and other vulnerable populations.
In Amagasaki City alone, damages from phone fraud in 2021 amounted to approximately 97 million yen (about 830,000 USD). To alleviate this problem and design new tools to combat fraud, from March 30 to March 31, 2022 the three parties will conduct simulations of realistic fraud scenarios in field trials with senior citizens from Amagasaki City, leveraging Fujitsu's human sensing technology to detect changes in human emotions in tandem with a methodology to measure and scale human emotions developed by Toyo University.
Professor Masayuki Kiriu, Department of Social Psychology, Faculty of Sociology, Toyo University comments, "the field trials will focus on the relationship between perpetrators and victims of phone scams and offer more concrete and effective fraud prevention measures. This project focuses specifically on the emotional and physical changes of victims, which is a field where research has not made much progress to date, with the goal of realizing an AI technology that can intervene to prevent phone fraud. We can call this an unprecedented and empathetic approach to dealing with phone fraud that places special emphasis on the feelings of victims."
Based on data and insights gained during these initial trials, the three parties will conduct further verification trials in the first half of fiscal 2022 to determine the accuracy of Fujitsu's AI model for phone fraud detection.
Innovation through converging technologies to combat a growing social problem
According to the Japanese National Police Agency, senior citizens aged 65 or older accounted for 88.2% of reported phone fraud cases in Japan in 2021, highlighting the vulnerability of this age group to phone frauds. While special fraud-prevention campaigns to deepen collaboration between anti-crime organizations and the police to strengthen patrols at ATMs, etc., the damage caused by phone fraud in Amagasaki City alone in 2021 amounted to approx. 97 million yen (approx. 831,000 USD) for 102 reported cases that year(4).
Amidst the growing number of people over 65 in Japan and many parts of the world this problem represents an increasingly urgent priority. To address this, Fujitsu, Toyo University and Amagasaki City started joint research toward the development of an AI model that detects phone fraud with high accuracy, leveraging technologies that combine Fujitsu's AI based sensing technology and Toyo University's research results on psychology and the emotional state of victims of criminal incidents.
Overview of the joint research
1. Research period:
February 17, 2022 to March 31, 2023
2. Research contents of the joint research
- Preparation phase: Development of test scenarios
Fujitsu and Toyo University analyzed keywords and patterns specific to phone fraud based on voice recordings of actual cases provided by the Hyogo Prefectural Police to create realistic phone fraud scenarios for use in the field trials.
- Field trials: Measurement data from senior citizens
The three parties will conduct field trials at the Amagasaki City Hall on March 30 and 31, 2022 with approx. twenty senior citizen volunteers from Amagasaki City as participants. Based on the phone fraud scenario created in advance, a phone call with a pre-recorded voice is made to the individual participants to simulate phone calls by a phone fraud group.
Fujitsu will leverage its "Actlyzer" AI technology for video-based behavioral analysis(5), its AI technology for facial expression recognition to detect changes in human emotions and its AI technology for real time pulse estimation based on facial images to measure and record data (including facial expressions and pulse data) of the participants.
After the phone calls, the participants will further reply to a questionnaire to measure their emotional state during the phone calls.
- Evaluation phase: Analysis of results and development of AI model for detection of phone fraud
Toyo University will analyze the actual data from participants measured during the trials and compare it to individual questionnaire results to identify the relationship between participants' physical and emotional state. Fujitsu will use this analysis to create an AI model to detect possible instances of phone fraud based on characteristics of participants that were (assumed to be) deceived during the simulations. The three parties will conduct a second field trial using this AI model in the first half of fiscal 2022 to confirm its accuracy in detecting phone fraud. Fujitsu aims to develop an AI model that can detect a range of different types of phone scams with high accuracy by the end of FY 2022.
3. Roles and responsibilities
Fujitsu:
- Development of test scenarios for the field trials
- Exploration and implementation of test methods, data collection
- Design and development of AI models for detection of phone fraud
Toyo University:
- Development of test scenarios for the field trials
- Psychological analysis of trial results, data collection
- Design of an AI model for detection of phone fraud
Amagasaki City:
- Providing participants and environment (test site) for the field trials
Future Plans
Focusing on the needs and challenges of a rapidly ageing society, the three parties aim to develop an AI model that is able to protect possible victims from increasingly complex and sophisticated phone scams and ultimately contribute to a safer society.
Comment from Daiki Masumoto, Fellow, SVP, Head of Advanced Converging Technologies Laboratories, Fujitsu Research, Fujitsu Limited
"We were impressed by the advanced initiatives of Amagasaki City to protect senior citizens from phone fraud, as well as Professor Kiriu's long history of activities to prevent such frauds. This is one reason why we are researching converging technologies that combine knowledge from different fields. Using this research as a starting point, we aim to realize a sustainable society where elderly people can live safely and securely."
Comment from Mayor Kazumi Inamura of Amagasaki City
"Since fiscal 2018, Amagasaki City has been tackling phone fraud in cooperation with the Hyogo Prefectural Police Headquarters and other organizations. We hope that this joint research will lead to the prevention of phone frauds not only in this city, but also all over Japan."
(1) Amagasaki City :
Location: Hyogo Prefecture, Japan; Mayor: Kazumi Inamura
(2) Converging technologies :
Advanced technologies that combine computer sciences and knowledge from the humanities and social sciences, aiming to solve diverse and complex issues. The joint research will focus on the research and development of converging technologies that combine AI and criminal psychology, in order to eradicate the increasing complexity and sophistication of phone frauds.
(3) Developing an AI model capable of detecting various types of phone fraud :
Fujitsu respects the privacy of involved parties and takes appropriate measures when handling personal data.
(4) Number of reported cases of phone fraud in Japan in 2021 :
Japanese Police Agency press release "Report on phone fraud in 2021 (reported numbers and arrests)." bit.ly/3uqqzCz (in Japanese)
(5) "Actlyzer" AI technology for video-based behavioral analysis :
"Fujitsu Develops New 'Actlyzer' AI Technology for Video-Based Behavioral Analysis" (press release, November 25, 2019).
This technology has been commercialized as an AI image analysis solution "FUJITSU Technical Computing Solution GREENAGES Citywide Surveillance".
About Fujitsu
Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 126,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 3.6 trillion yen (US$34 billion) for the fiscal year ended March 31, 2021. For more information, please see www.fujitsu.com.
About Toyo University
Toyo University is one of Japan's comprehensive universities with many specialized academic fields, and more than 30,000 students enrolled now. In 2014, the university was selected as a university under the Top Global University Project carried out by the Ministry of Education, Culture, Sports, Science and Technology, and is accelerating the development of global human resources who will play active roles in the international arena. For more information, please see www.toyo.ac.jp.
Public Relations Section:
Toyo University Incorporated Educational Institution
Phone : +81-3-3945-7571
E-mail : mlkoho@toyo.jp
Source: Fujitsu Ltd
Copyright 2022 JCN Newswire . All rights reserved.
In Amagasaki City alone, damages from phone fraud in 2021 amounted to approximately 97 million yen (about 830,000 USD). To alleviate this problem and design new tools to combat fraud, from March 30 to March 31, 2022 the three parties will conduct simulations of realistic fraud scenarios in field trials with senior citizens from Amagasaki City, leveraging Fujitsu's human sensing technology to detect changes in human emotions in tandem with a methodology to measure and scale human emotions developed by Toyo University.
Professor Masayuki Kiriu, Department of Social Psychology, Faculty of Sociology, Toyo University comments, "the field trials will focus on the relationship between perpetrators and victims of phone scams and offer more concrete and effective fraud prevention measures. This project focuses specifically on the emotional and physical changes of victims, which is a field where research has not made much progress to date, with the goal of realizing an AI technology that can intervene to prevent phone fraud. We can call this an unprecedented and empathetic approach to dealing with phone fraud that places special emphasis on the feelings of victims."
Based on data and insights gained during these initial trials, the three parties will conduct further verification trials in the first half of fiscal 2022 to determine the accuracy of Fujitsu's AI model for phone fraud detection.
Innovation through converging technologies to combat a growing social problem
According to the Japanese National Police Agency, senior citizens aged 65 or older accounted for 88.2% of reported phone fraud cases in Japan in 2021, highlighting the vulnerability of this age group to phone frauds. While special fraud-prevention campaigns to deepen collaboration between anti-crime organizations and the police to strengthen patrols at ATMs, etc., the damage caused by phone fraud in Amagasaki City alone in 2021 amounted to approx. 97 million yen (approx. 831,000 USD) for 102 reported cases that year(4).
Amidst the growing number of people over 65 in Japan and many parts of the world this problem represents an increasingly urgent priority. To address this, Fujitsu, Toyo University and Amagasaki City started joint research toward the development of an AI model that detects phone fraud with high accuracy, leveraging technologies that combine Fujitsu's AI based sensing technology and Toyo University's research results on psychology and the emotional state of victims of criminal incidents.
Overview of the joint research
1. Research period:
February 17, 2022 to March 31, 2023
2. Research contents of the joint research
- Preparation phase: Development of test scenarios
Fujitsu and Toyo University analyzed keywords and patterns specific to phone fraud based on voice recordings of actual cases provided by the Hyogo Prefectural Police to create realistic phone fraud scenarios for use in the field trials.
- Field trials: Measurement data from senior citizens
The three parties will conduct field trials at the Amagasaki City Hall on March 30 and 31, 2022 with approx. twenty senior citizen volunteers from Amagasaki City as participants. Based on the phone fraud scenario created in advance, a phone call with a pre-recorded voice is made to the individual participants to simulate phone calls by a phone fraud group.
Fujitsu will leverage its "Actlyzer" AI technology for video-based behavioral analysis(5), its AI technology for facial expression recognition to detect changes in human emotions and its AI technology for real time pulse estimation based on facial images to measure and record data (including facial expressions and pulse data) of the participants.
After the phone calls, the participants will further reply to a questionnaire to measure their emotional state during the phone calls.
- Evaluation phase: Analysis of results and development of AI model for detection of phone fraud
Toyo University will analyze the actual data from participants measured during the trials and compare it to individual questionnaire results to identify the relationship between participants' physical and emotional state. Fujitsu will use this analysis to create an AI model to detect possible instances of phone fraud based on characteristics of participants that were (assumed to be) deceived during the simulations. The three parties will conduct a second field trial using this AI model in the first half of fiscal 2022 to confirm its accuracy in detecting phone fraud. Fujitsu aims to develop an AI model that can detect a range of different types of phone scams with high accuracy by the end of FY 2022.
3. Roles and responsibilities
Fujitsu:
- Development of test scenarios for the field trials
- Exploration and implementation of test methods, data collection
- Design and development of AI models for detection of phone fraud
Toyo University:
- Development of test scenarios for the field trials
- Psychological analysis of trial results, data collection
- Design of an AI model for detection of phone fraud
Amagasaki City:
- Providing participants and environment (test site) for the field trials
Future Plans
Focusing on the needs and challenges of a rapidly ageing society, the three parties aim to develop an AI model that is able to protect possible victims from increasingly complex and sophisticated phone scams and ultimately contribute to a safer society.
Comment from Daiki Masumoto, Fellow, SVP, Head of Advanced Converging Technologies Laboratories, Fujitsu Research, Fujitsu Limited
"We were impressed by the advanced initiatives of Amagasaki City to protect senior citizens from phone fraud, as well as Professor Kiriu's long history of activities to prevent such frauds. This is one reason why we are researching converging technologies that combine knowledge from different fields. Using this research as a starting point, we aim to realize a sustainable society where elderly people can live safely and securely."
Comment from Mayor Kazumi Inamura of Amagasaki City
"Since fiscal 2018, Amagasaki City has been tackling phone fraud in cooperation with the Hyogo Prefectural Police Headquarters and other organizations. We hope that this joint research will lead to the prevention of phone frauds not only in this city, but also all over Japan."
(1) Amagasaki City :
Location: Hyogo Prefecture, Japan; Mayor: Kazumi Inamura
(2) Converging technologies :
Advanced technologies that combine computer sciences and knowledge from the humanities and social sciences, aiming to solve diverse and complex issues. The joint research will focus on the research and development of converging technologies that combine AI and criminal psychology, in order to eradicate the increasing complexity and sophistication of phone frauds.
(3) Developing an AI model capable of detecting various types of phone fraud :
Fujitsu respects the privacy of involved parties and takes appropriate measures when handling personal data.
(4) Number of reported cases of phone fraud in Japan in 2021 :
Japanese Police Agency press release "Report on phone fraud in 2021 (reported numbers and arrests)." bit.ly/3uqqzCz (in Japanese)
(5) "Actlyzer" AI technology for video-based behavioral analysis :
"Fujitsu Develops New 'Actlyzer' AI Technology for Video-Based Behavioral Analysis" (press release, November 25, 2019).
This technology has been commercialized as an AI image analysis solution "FUJITSU Technical Computing Solution GREENAGES Citywide Surveillance".
About Fujitsu
Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 126,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 3.6 trillion yen (US$34 billion) for the fiscal year ended March 31, 2021. For more information, please see www.fujitsu.com.
About Toyo University
Toyo University is one of Japan's comprehensive universities with many specialized academic fields, and more than 30,000 students enrolled now. In 2014, the university was selected as a university under the Top Global University Project carried out by the Ministry of Education, Culture, Sports, Science and Technology, and is accelerating the development of global human resources who will play active roles in the international arena. For more information, please see www.toyo.ac.jp.
Public Relations Section:
Toyo University Incorporated Educational Institution
Phone : +81-3-3945-7571
E-mail : mlkoho@toyo.jp
Source: Fujitsu Ltd
Copyright 2022 JCN Newswire . All rights reserved.
Data & News supplied by www.cloudquote.io
Stock quotes supplied by Barchart
Quotes delayed at least 20 minutes.
By accessing this page, you agree to the following
Privacy Policy and Terms and Conditions.
Stock quotes supplied by Barchart
Quotes delayed at least 20 minutes.
By accessing this page, you agree to the following
Privacy Policy and Terms and Conditions.