SlideShare a Scribd company logo
1 of 16
Download to read offline
How to choose
the Liveness solution
that best fits your needs
Serge Malgin
Biometry expert | Oz Forensics
info@ozforensics.com
info@ozforensics.com
• Introduction
• What makes the industry different today?
• New Generation of Attacks
• Active vs. Passive Liveness
• Client acquisition vs. risk
• Liveness solution must-have
• Can a scammer hack biometric authentication?
AGENDA
info@ozforensics.com
Oz Forensics —
biometric fraud prevention
software vendor.
WHO WE ARE
HQ — UAE
Offices — USA, Kazakhstan
Representatives — Australia, Brazil
Clients
Telecom Banks Fintech
Government
services
KYC
providers
Civil aviation
info@ozforensics.com
WHAT MAKES THE INDUSTRY DIFFERENT TODAY?
1. Post-Covid era = remote is the new norm.
2. Global biometric regulation is changing daily.
3. Local laws for biometric security
and data protection.
4. Constantly increasing biometry fraud.
THE TOTAL
IDENTITY FRAUD IMPACT
$52 billion of loss
affecting 42 million
U.S. consumer victims
— 2021*
*2022 Identity Fraud Study: The Virtual Battleground | Javelin (javelinstrategy.com)
info@ozforensics.com
Level 1
Up to 30 $
Level 2
300 $
Level 3
3000 $
DETECTING A LIVE PERSON
ISO Standard — 3 levels of attacks:
ISO/IEC 30107-3
To prepare an attack, an impostor would spend a certain
amount of money depending on how sophisticated their
attack is going to be.
info@ozforensics.com
Print
30%
Replay
69%
Other
Less than 1%
DAILY STATISTICS: 1. Over 1 M Liveness checks per day
2. Average 0,5 - 0,8% attacks on Liveness:
OUR STATISTICS
info@ozforensics.com
NEW GENERATION OF ATTACKS
CAMERA VULNERABILITIES
It is possible to deploy
deepfake videos straight into
the app evading verifications.
Deepfake is hard to detect by
a human, not all the algorithms
can detect it either.
Use of emulators to hack
the mobile apps.
info@ozforensics.com
ACTIVE
Upsides:
• Allows action/gesture, which means
consent. Can be used for potential legal
action.
PASSIVE
ACTIVE VS PASSIVE LIVENESS
Upsides:
• 1 process = 1 photo = 1 second.
• Keeps conversion as there is no action.
Downsides:
• Customer journey increases
up to 5 seconds.
• Lower conversion: 5-10%* of clients
can’t/don’t want to make a gesture.
Downsides:
• No consent as there is NO action.
*per Oz Forensics stats
info@ozforensics.com
ACTIVE VS PASSIVE LIVENESS TRENDS
OZ FORENSICS STATISTICS
TO STORE
OR NOT TO STORE?
Data storage = evidence base,
with data security risks
Not to store = to be 100%
reliant on technology
HOW WILL IT LOOK LIKE?
DIGITAL ARBITRAGE?
• Should have relevant competencies
• Ready to render verdict in disputable
cases
• Must 100% detect the deepfakes.
BUT HOW?
info@ozforensics.com
info@ozforensics.com
TWO WAYS TO CALCULATE LIVENESS CHECKS
Server-based Liveness:
On-device Liveness:
Try On-device
Liveness
on Google Play
now
info@ozforensics.com
TYPES OF LIVENESS PROCESSING
Liveness features Server-based On-device
Processing users’ image/video on the server on user’s device
Stable Internet connection required yes not required
ISO 30107-3 iBeta Level 1&2 certification yes yes
Fast deployment and integration with REST API yes yes
Speed 1000 RPS yes not required
Horizontal scaling yes not required
SLA 99% availability yes not required
iOS/Android SDK yes yes
WEB SDK yes no
Flexible interface customization yes yes
info@ozforensics.com
OTHER ISSUES CHOOSING A LIVENESS SOLUTION
1. Unclear expectations • What do you want to achieve?
3. No Flexibility in the solution • SaaS/On-premise server-based
• On-device
4. Difficulties using the interface • Intuitive interface
• Multiple SDKs
5. Weak SLAs and Tech support • Do you want an accurate
and well supported system?
6. Scalability • How fast do you want to increase your server
capacity?
2. Robustness • ISO/IEC 30107-3 (iBeta Level 1&2)
• Camera spoofing detection
info@ozforensics.com
HOW CAN WE HELP?
Talk to us
Tell us about your requirements,
and we help you to choose
the best solution.
Test with us
Choose what works for you well:
testing Liveness checks
and viewing statistics or full-scale
pilot project with integrating
into your infrastructure.
Proof with us
We organise a working chat
with our experts
and they are happy to help you
at every stage of a PoC.
1 2 3
info@ozforensics.com
MEET THE ATTACKER
What you see is a deepfake, not a real person. Pretty hard to detect, isn’t it?
Thank you!
Serge Malgin
Biometry expert | Oz Forensics
20 years in global software industry
of cyber security and fraud prevention
info@ozforensics.com

More Related Content

Similar to Guide - How to choose Liveness detection - Oz Forensics

HTML5 vs. Native Apps: Demystifying the Decision Making Process
HTML5 vs. Native Apps: Demystifying the Decision Making ProcessHTML5 vs. Native Apps: Demystifying the Decision Making Process
HTML5 vs. Native Apps: Demystifying the Decision Making ProcessiTexico
 
Oath appsec sf 2015 dem rev. 2
Oath appsec sf 2015 dem rev. 2Oath appsec sf 2015 dem rev. 2
Oath appsec sf 2015 dem rev. 2Donald Malloy
 
Strong Authentication - Open Source
Strong Authentication - Open SourceStrong Authentication - Open Source
Strong Authentication - Open SourceDonald Malloy
 
Strategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdfStrategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdfKMSSolutionsMarketin
 
Building an AppSec Team Extended Cut
Building an AppSec Team Extended CutBuilding an AppSec Team Extended Cut
Building an AppSec Team Extended CutMike Spaulding
 
Mike Spaulding - Building an Application Security Program
Mike Spaulding - Building an Application Security ProgramMike Spaulding - Building an Application Security Program
Mike Spaulding - Building an Application Security Programcentralohioissa
 
Securing Systems - Still Crazy After All These Years
Securing Systems - Still Crazy After All These YearsSecuring Systems - Still Crazy After All These Years
Securing Systems - Still Crazy After All These YearsAdrian Sanabria
 
LSI Spring Agent Open House 2014
LSI Spring Agent Open House 2014LSI Spring Agent Open House 2014
LSI Spring Agent Open House 2014Ashlie Steele
 
Brighttalk what should we be monitoring - final
Brighttalk   what should we be monitoring - finalBrighttalk   what should we be monitoring - final
Brighttalk what should we be monitoring - finalAndrew White
 
2018 01 smart city symposium - db
2018 01 smart city symposium - db2018 01 smart city symposium - db
2018 01 smart city symposium - dbDavid Bressler
 
Bio catch
Bio catchBio catch
Bio catchYanivt
 
The Evolution of Cybercrime
The Evolution of CybercrimeThe Evolution of Cybercrime
The Evolution of CybercrimeStephen Cobb
 
3. introduction to software testing
3. introduction to software testing3. introduction to software testing
3. introduction to software testingChandra Maddigapu
 
Markus Paasovaara: Face recognition
Markus Paasovaara: Face recognitionMarkus Paasovaara: Face recognition
Markus Paasovaara: Face recognitionFuturice
 
i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...
i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...
i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...ProductNation/iSPIRT
 
The Top 7 Causes of Major Security Breaches
The Top 7 Causes of Major Security BreachesThe Top 7 Causes of Major Security Breaches
The Top 7 Causes of Major Security BreachesKaseya
 
Streamlining AppSec Policy Definition.pptx
Streamlining AppSec Policy Definition.pptxStreamlining AppSec Policy Definition.pptx
Streamlining AppSec Policy Definition.pptxtmbainjr131
 
Mobile Automation: Lessons From The Trenches
Mobile Automation: Lessons From The TrenchesMobile Automation: Lessons From The Trenches
Mobile Automation: Lessons From The TrenchesAshok Karania
 
Real Devices or Emulators: Wen to use What for Automated Testing
Real Devices or Emulators: Wen to use What for Automated TestingReal Devices or Emulators: Wen to use What for Automated Testing
Real Devices or Emulators: Wen to use What for Automated TestingSauce Labs
 

Similar to Guide - How to choose Liveness detection - Oz Forensics (20)

HTML5 vs. Native Apps: Demystifying the Decision Making Process
HTML5 vs. Native Apps: Demystifying the Decision Making ProcessHTML5 vs. Native Apps: Demystifying the Decision Making Process
HTML5 vs. Native Apps: Demystifying the Decision Making Process
 
Oath appsec sf 2015 dem rev. 2
Oath appsec sf 2015 dem rev. 2Oath appsec sf 2015 dem rev. 2
Oath appsec sf 2015 dem rev. 2
 
Strong Authentication - Open Source
Strong Authentication - Open SourceStrong Authentication - Open Source
Strong Authentication - Open Source
 
Strategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdfStrategies for Choosing eKYC Solutions.pdf
Strategies for Choosing eKYC Solutions.pdf
 
Building an AppSec Team Extended Cut
Building an AppSec Team Extended CutBuilding an AppSec Team Extended Cut
Building an AppSec Team Extended Cut
 
Mike Spaulding - Building an Application Security Program
Mike Spaulding - Building an Application Security ProgramMike Spaulding - Building an Application Security Program
Mike Spaulding - Building an Application Security Program
 
Securing Systems - Still Crazy After All These Years
Securing Systems - Still Crazy After All These YearsSecuring Systems - Still Crazy After All These Years
Securing Systems - Still Crazy After All These Years
 
LSI Spring Agent Open House 2014
LSI Spring Agent Open House 2014LSI Spring Agent Open House 2014
LSI Spring Agent Open House 2014
 
Brighttalk what should we be monitoring - final
Brighttalk   what should we be monitoring - finalBrighttalk   what should we be monitoring - final
Brighttalk what should we be monitoring - final
 
2018 01 smart city symposium - db
2018 01 smart city symposium - db2018 01 smart city symposium - db
2018 01 smart city symposium - db
 
Bio catch
Bio catchBio catch
Bio catch
 
The Evolution of Cybercrime
The Evolution of CybercrimeThe Evolution of Cybercrime
The Evolution of Cybercrime
 
3. introduction to software testing
3. introduction to software testing3. introduction to software testing
3. introduction to software testing
 
Mobile Security
Mobile SecurityMobile Security
Mobile Security
 
Markus Paasovaara: Face recognition
Markus Paasovaara: Face recognitionMarkus Paasovaara: Face recognition
Markus Paasovaara: Face recognition
 
i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...
i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...
i7 Networks - Presentation at Zensar #TechShowcase - An iSPIRT ProductNation ...
 
The Top 7 Causes of Major Security Breaches
The Top 7 Causes of Major Security BreachesThe Top 7 Causes of Major Security Breaches
The Top 7 Causes of Major Security Breaches
 
Streamlining AppSec Policy Definition.pptx
Streamlining AppSec Policy Definition.pptxStreamlining AppSec Policy Definition.pptx
Streamlining AppSec Policy Definition.pptx
 
Mobile Automation: Lessons From The Trenches
Mobile Automation: Lessons From The TrenchesMobile Automation: Lessons From The Trenches
Mobile Automation: Lessons From The Trenches
 
Real Devices or Emulators: Wen to use What for Automated Testing
Real Devices or Emulators: Wen to use What for Automated TestingReal Devices or Emulators: Wen to use What for Automated Testing
Real Devices or Emulators: Wen to use What for Automated Testing
 

Recently uploaded

What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number SystemsJheuzeDellosa
 
DNT_Corporate presentation know about us
DNT_Corporate presentation know about usDNT_Corporate presentation know about us
DNT_Corporate presentation know about usDynamic Netsoft
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVshikhaohhpro
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfjoe51371421
 
Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)OPEN KNOWLEDGE GmbH
 
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio, Inc.
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...stazi3110
 
Professional Resume Template for Software Developers
Professional Resume Template for Software DevelopersProfessional Resume Template for Software Developers
Professional Resume Template for Software DevelopersVinodh Ram
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...harshavardhanraghave
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxComplianceQuest1
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...gurkirankumar98700
 
Cloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStackCloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStackVICTOR MAESTRE RAMIREZ
 
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...Christina Lin
 
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfThe Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfkalichargn70th171
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comFatema Valibhai
 
Engage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyEngage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyFrank van der Linden
 
Project Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationProject Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationkaushalgiri8080
 
chapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptchapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptkotipi9215
 

Recently uploaded (20)

What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number Systems
 
DNT_Corporate presentation know about us
DNT_Corporate presentation know about usDNT_Corporate presentation know about us
DNT_Corporate presentation know about us
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdf
 
Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)
 
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
 
Professional Resume Template for Software Developers
Professional Resume Template for Software DevelopersProfessional Resume Template for Software Developers
Professional Resume Template for Software Developers
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docx
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
 
Cloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStackCloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStack
 
Exploring iOS App Development: Simplifying the Process
Exploring iOS App Development: Simplifying the ProcessExploring iOS App Development: Simplifying the Process
Exploring iOS App Development: Simplifying the Process
 
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
ODSC - Batch to Stream workshop - integration of Apache Spark, Cassandra, Pos...
 
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfThe Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.com
 
Engage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyEngage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The Ugly
 
Project Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationProject Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanation
 
chapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptchapter--4-software-project-planning.ppt
chapter--4-software-project-planning.ppt
 
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
 

Guide - How to choose Liveness detection - Oz Forensics

  • 1. How to choose the Liveness solution that best fits your needs Serge Malgin Biometry expert | Oz Forensics info@ozforensics.com
  • 2. info@ozforensics.com • Introduction • What makes the industry different today? • New Generation of Attacks • Active vs. Passive Liveness • Client acquisition vs. risk • Liveness solution must-have • Can a scammer hack biometric authentication? AGENDA
  • 3. info@ozforensics.com Oz Forensics — biometric fraud prevention software vendor. WHO WE ARE HQ — UAE Offices — USA, Kazakhstan Representatives — Australia, Brazil Clients Telecom Banks Fintech Government services KYC providers Civil aviation
  • 4. info@ozforensics.com WHAT MAKES THE INDUSTRY DIFFERENT TODAY? 1. Post-Covid era = remote is the new norm. 2. Global biometric regulation is changing daily. 3. Local laws for biometric security and data protection. 4. Constantly increasing biometry fraud. THE TOTAL IDENTITY FRAUD IMPACT $52 billion of loss affecting 42 million U.S. consumer victims — 2021* *2022 Identity Fraud Study: The Virtual Battleground | Javelin (javelinstrategy.com)
  • 5. info@ozforensics.com Level 1 Up to 30 $ Level 2 300 $ Level 3 3000 $ DETECTING A LIVE PERSON ISO Standard — 3 levels of attacks: ISO/IEC 30107-3 To prepare an attack, an impostor would spend a certain amount of money depending on how sophisticated their attack is going to be.
  • 6. info@ozforensics.com Print 30% Replay 69% Other Less than 1% DAILY STATISTICS: 1. Over 1 M Liveness checks per day 2. Average 0,5 - 0,8% attacks on Liveness: OUR STATISTICS
  • 7. info@ozforensics.com NEW GENERATION OF ATTACKS CAMERA VULNERABILITIES It is possible to deploy deepfake videos straight into the app evading verifications. Deepfake is hard to detect by a human, not all the algorithms can detect it either. Use of emulators to hack the mobile apps.
  • 8. info@ozforensics.com ACTIVE Upsides: • Allows action/gesture, which means consent. Can be used for potential legal action. PASSIVE ACTIVE VS PASSIVE LIVENESS Upsides: • 1 process = 1 photo = 1 second. • Keeps conversion as there is no action. Downsides: • Customer journey increases up to 5 seconds. • Lower conversion: 5-10%* of clients can’t/don’t want to make a gesture. Downsides: • No consent as there is NO action. *per Oz Forensics stats
  • 9. info@ozforensics.com ACTIVE VS PASSIVE LIVENESS TRENDS OZ FORENSICS STATISTICS
  • 10. TO STORE OR NOT TO STORE? Data storage = evidence base, with data security risks Not to store = to be 100% reliant on technology HOW WILL IT LOOK LIKE? DIGITAL ARBITRAGE? • Should have relevant competencies • Ready to render verdict in disputable cases • Must 100% detect the deepfakes. BUT HOW? info@ozforensics.com
  • 11. info@ozforensics.com TWO WAYS TO CALCULATE LIVENESS CHECKS Server-based Liveness: On-device Liveness: Try On-device Liveness on Google Play now
  • 12. info@ozforensics.com TYPES OF LIVENESS PROCESSING Liveness features Server-based On-device Processing users’ image/video on the server on user’s device Stable Internet connection required yes not required ISO 30107-3 iBeta Level 1&2 certification yes yes Fast deployment and integration with REST API yes yes Speed 1000 RPS yes not required Horizontal scaling yes not required SLA 99% availability yes not required iOS/Android SDK yes yes WEB SDK yes no Flexible interface customization yes yes
  • 13. info@ozforensics.com OTHER ISSUES CHOOSING A LIVENESS SOLUTION 1. Unclear expectations • What do you want to achieve? 3. No Flexibility in the solution • SaaS/On-premise server-based • On-device 4. Difficulties using the interface • Intuitive interface • Multiple SDKs 5. Weak SLAs and Tech support • Do you want an accurate and well supported system? 6. Scalability • How fast do you want to increase your server capacity? 2. Robustness • ISO/IEC 30107-3 (iBeta Level 1&2) • Camera spoofing detection
  • 14. info@ozforensics.com HOW CAN WE HELP? Talk to us Tell us about your requirements, and we help you to choose the best solution. Test with us Choose what works for you well: testing Liveness checks and viewing statistics or full-scale pilot project with integrating into your infrastructure. Proof with us We organise a working chat with our experts and they are happy to help you at every stage of a PoC. 1 2 3
  • 15. info@ozforensics.com MEET THE ATTACKER What you see is a deepfake, not a real person. Pretty hard to detect, isn’t it?
  • 16. Thank you! Serge Malgin Biometry expert | Oz Forensics 20 years in global software industry of cyber security and fraud prevention info@ozforensics.com