dualitytech.com Open in urlscan Pro
2600:9000:237d:b600:2:d710:2680:93a1  Public Scan

Form analysis
3 forms found in the DOM

GET https://dualitytech.com/search/

<form class="elementor-search-form" role="search" action="https://dualitytech.com/search/" method="get">
  <div class="elementor-search-form__container">
    <div class="elementor-search-form__icon">
      <i aria-hidden="true" class="fas fa-search"></i> <span class="elementor-screen-only">Search</span>
    </div>
    <input placeholder="Search..." class="elementor-search-form__input" type="search" name="q" title="Search" value="">
  </div>
</form>

GET https://dualitytech.com/search/

<form class="elementor-search-form" role="search" action="https://dualitytech.com/search/" method="get">
  <div class="elementor-search-form__container">
    <div class="elementor-search-form__icon">
      <i aria-hidden="true" class="fas fa-search"></i> <span class="elementor-screen-only">Search</span>
    </div>
    <input placeholder="Search..." class="elementor-search-form__input" type="search" name="q" title="Search" value="">
  </div>
</form>

POST #

<form class="acsb-form" data-acsb-search="form" enctype="multipart/form-data" action="#" method="POST"> <input type="text" tabindex="0" name="acsb_search" autocomplete="off" placeholder="Unclear content? Search in dictionary..."
    aria-label="Unclear content? Search in dictionary..."> <i class="acsbi-search"></i> <i class="acsbi-chevron_down"></i> </form>

Text Content

Use Website In a Screen-Reader Mode
Skip to Content
↵ENTER
Skip to Menu
↵ENTER
Skip to Footer
↵ENTER

Consent to Cookies & Data processing
On this website we use cookies and similar functions to process end device
information and personal data. The processing is used for purposes such as to
integrate content, external services and elements from third parties,
statistical analysis/measurement, personalized advertising and the integration
of social media. Depending on the function, data is passed on to up to 22 third
parties and processed by them. This consent is voluntary, not required for the
use of our website and can be revoked at any time using the icon on the bottom
left.
Function
Marketing
Preferences
Measurement
Other
Social media
Reject all Accept allSave + Exit
Customize your choice | Cookies | Privacy notice

powered by consentmanager.net

Skip to content
Platform


PLATFORM OVERVIEW




QUERY ENGINE


MACHINE LEARNING AND ANALYTICS


OPEN SOURCE TECH


Use Case


FINANCIAL SERVICES




FRAUD PREVENTION


ANTI MONEY LAUNDERING


TRADE FINANCING


GOVERNMENT




SECURE INVESTIGATIONS


HEALTHCARE




REAL WORLD EVIDENCE


GENOME WIDE ASSOCIATION STUDIES


OTHER




TARGETED OFFERS

Partners


TECHNOLOGY




GOOGLE


IBM


INTEL


ORACLE


OPEN SOURCE




OPEN FHE

Resources


BLOG


RESOURCE HUB


DEMO LIBRARY

Company


ABOUT US


EVENTS


NEWS


CAREERS

Contact us

Search
 * Platform
   
   
   * * * PLATFORM OVERVIEW
         
         
         
         
         QUERY ENGINE
         
         
         MACHINE LEARNING AND ANALYTICS
         
         
         OPEN SOURCE TECH
         
         
 * Use Case
   
   
   * * * FINANCIAL SERVICES
         
         
         
         
         FRAUD PREVENTION
         
         
         ANTI MONEY LAUNDERING
         
         
         TRADE FINANCING
         
         
         GOVERNMENT
         
         
         
         
         SECURE INVESTIGATIONS
         
         
         HEALTHCARE
         
         
         
         
         REAL WORLD EVIDENCE
         
         
         GENOME WIDE ASSOCIATION STUDIES
         
         
         OTHER
         
         
         
         
         TARGETED OFFERS
 * Partners
   
   
   * * * COLLABORATION HUB
         
         
         
         
         GOOGLE
         
         
         IBM
         
         
         INTEL
         
         
         ORACLE
         
         
         
 * Resources
   
   
   * * * BLOG
         
         
         RESOURCE HUB
         
         
         DEMO LIBRARY
 * Company
   
   
   * * * ABOUT US
         
         
         EVENTS
         
         
         NEWS
         
         
         CAREERS

Contact us

Search
Back


SECURE FEDERATED LEARNING: PROTECTING THE DATA AND THE MODEL


Omer Moran|
February 22, 2023


Learn more about secure, collaborative computing Request a demo


Back


SECURE FEDERATED LEARNING: PROTECTING THE DATA AND THE MODEL

Omer Moran|
February 22, 2023


Learn more about secure, collaborative computing Request a demo


Post


INTRODUCTION TO SECURE FEDERATED LEARNING

Federated Learning (FL) is a distributed machine learning (ML) technique that
enables model training on data from multiple, decentralized servers with local
data samples, without exchanging or moving data. This approach ensures that the
data remains in its original location and is not exposed to any other parties.

Another characteristic of FL is that it is typically composed of heterogeneous
datasets where the size of the dataset varies from one data owner to another.  

In this blog, we will provide different examples of how FL is being used today
and its advantages when supporting secured data collaboration projects. From
there we will move to discuss the current limitations and advantages, and we
will finish by introducing Duality’s Secured Federated Learning (SFL). 

A classic example of FL is in the prediction of autocomplete in keyboards. By
analyzing data from a user’s keystrokes, a ML model can be trained to predict
the next word or phrase the user is likely to type. In the keyboard example, the
model is trained locally on each of the mobile devices of the users, and then
aggregated in a centralized compute node, then distributed back to the mobile
devices.

Another interesting example of FL can be found  within healthcare. FL can be
used to securely aggregate model training results of data from multiple sources,
to improve the ability in identifying high-risk patients, discover biomarkers
that could indicate a certain disease is present, and much more. These
collaboration scenarios require data from multiple hospitals and/or clinics, and
can be extremely difficult to share without violating privacy laws.


TYPES OF FEDERATED LEARNING 

FL can be used in various use cases, and consequently there are specific
implementations and adjustments that are made to best accommodate each scenario.
At a high level, there are three topics for consideration:

 1. Communication Pattern – centralized vs decentralized.  The centralized mode
    offers a deployment of a star-based network topology. The participants in
    the collaboration communicate through a centralized node  (referred as the
    “Hub”) which is responsible for receiving the partial model results,
    aggregating it, and distributing the new model to the participants. The
    decentralized mode offers deployments of a mesh topology that provide
    communications directly among peers. Participating nodes coordinate among
    themselves to train and update a shared model with their localized data,
    without reliance on a central server.
 2. Data Partitioning – Horizontal vs Vertical. Horizontal federated analysis
    enable to train a model or run analysis on data that shares the same data
    schema. Meaning if you would like to train a model but your dataset is “too
    small” for analysis (not enough rows in the data), using horizontal FL you
    can train your model on multiple datasets while the data remains local.
    Vertical partitioning comes into play when your data includes insufficient
    features (columns). In this case two (or more) datasets are linked using a
    mutual ID, which enable enrichment of additional features.
 3. Hardware – homogeneous / heterogeneous. Homogeneous FL is the standard
    version in which the end devices all share the same characteristics.
    Heterogeneous FL is increasingly being applied in scenarios which involve
    multiple kinds of data owners, like devices that use the internet of things
    (IoT). The unique characteristics of IoT devices, such as their limited
    computational power, intermittent network connectivity, and distributed
    nature, necessitate tailored approaches for FL to achieve optimal
    performance and computations resources allocation.


LIMITATIONS AND DISADVANTAGES OF STANDARD FEDERATED LEARNING 

One of the main disadvantages of standard FL is the fact that the model runs in
the clear. This means that the data owner who holds the data has visibility to
the model being run on their data, thus putting the model at risk. For example,
if a company has developed a proprietary model that can be used in the insurance
industry, running the model on an insurance company’s real data can expose it
and make it susceptible to copying.

Another problem with the use of FL is the potential for data leakage during
model training. In FL, each of the nodes (edge devices) performs the computation
locally and then sends their partial results to the centralized server. The
server performs aggregation of the partial results and distributes the model to
the nodes. This process is called an iteration and can be repeated as many times
as needed to train the model. The security mechanism of standard FL is based on
data aggregation, and therefore it implies statistical security for the private
data. Academic studies show that based on the iterations and partial results,
one can derive input on the data itself.


DUALITY INTRODUCES CRYPTOGRAPHIC SECURE FEDERATED LEARNING 

To overcome the limitations of FL, Duality introduces Secure Federated Learning
(SFL). SFL adds an extra layer of cryptographic encryption to the standard FL,
which encrypts the partial results sent between the data owners and the
centralized server. This encryption will prevent data leakage and will keep the
trained model concealed from the data owners.

Unlike the typical FL approach where security is based on statistical
considerations (and therefore relatively easy to hack), Duality added security
of a cryptographic secure protocol ensures a clear security measure (typically
equivalent to 128 or 256-bit AES).

Duality’s cryptographic SFL approach combines various cryptography techniques
and federated learning (FL). Specifically, our solution leverages fully
homomorphic encryption (FHE) and secure multiparty computation (sMPC) to create
a novel cryptographic protocol that overcomes the performance limitations of
FHE.


THE DUALITY APPROACH TO PRIVACY ENHANCING TECHNOLOGIES

Our approach at Duality is such that there is no one PET fits all, rather use a
wide range of PET technologies and adjust the right PET per case. Thus, we’ve
added FL to our technology stack in addition to fully homomorphic encryption and
MPC. 

Duality supports a wide range of algorithms and frameworks for training and
inference in a secured environment. In our latest release, we introduced a new
option to train logistic regression models with cryptographic SFL. This is done
using a FL approach with an additional layer of cryptographic security, which
makes it more secure than a typical federated learning framework.

This design provides rigorous and practical privacy-preserving machine learning
for data collaboration in real-world challenges. Our unique strategy is based on
theoretical and applied research in cryptography and algorithms. Moreover, it is
delivered in a user-friendly platform that allows users to utilize this
technique without requiring any cryptographic knowledge.


CONCLUSION

Federated Learning is a powerful technique that has revolutionized the way
machine learning models are trained. However, it comes with its own set of
limitations and problems. Duality Technologies’ Secured Federated Learning (SFL)
is a solution that addresses these limitations and allows computations to train
models on sensitive data worry-free.

Click below to learn more about how PETs like FL are combined to solve business
problems.




You might also like


DATA CLEAN ROOMS: ADVANTAGES AND DISADVANTAGES

Phoebe Spanier March 28, 2023


WHAT IS A DATA CLEAN ROOM? WHAT DCRS CAN (AND CAN’T) DO

Phoebe Spanier March 21, 2023


INTEL, DUALITY, AND SECURITY IN LIFE SCIENCES 

Emory Walsh March 13, 2023


DUALITY DEEPENS INVESTMENT INTO GOVERNMENT SECTOR

Marcella Arthur February 23, 2023
Sign up for more knowledge and insights from our experts


Linkedin Twitter

ABOUT DUALITY

 * Company
 * Careers



PLATFORM

 * Platform Overview
 * Query Engine
 * Machine Learning and Analytics

INDUSTRY SOLUTIONS

 * Financial Services
 * Healthcare
 * Government



PARTNERS

 * Collaboration Hub
 * Intel
 * Oracle
 * IBM
 * Google



NEWS

 * Events
 * Blog



CONTACT US

SUBSCRIBE TO OUR MONTHLY NEWSLETTER



All rights reserved to © Duality 2022
 * Terms of Use
 * Privacy
 * Cookies Policy

Privacy settings

English
Accessibility Adjustments
Reset Settings Statement Hide Interface

Choose the right accessibility profile for you
OFF ON
Seizure Safe Profile Clear flashes & reduces color
This profile enables epileptic and seizure prone users to browse safely by
eliminating the risk of seizures that result from flashing or blinking
animations and risky color combinations.
OFF ON
Vision Impaired Profile Enhances website's visuals
This profile adjusts the website, so that it is accessible to the majority of
visual impairments such as Degrading Eyesight, Tunnel Vision, Cataract,
Glaucoma, and others.
OFF ON
ADHD Friendly Profile More focus & fewer distractions
This profile significantly reduces distractions, to help people with ADHD and
Neurodevelopmental disorders browse, read, and focus on the essential elements
of the website more easily.
OFF ON
Cognitive Disability Profile Assists with reading & focusing
This profile provides various assistive features to help users with cognitive
disabilities such as Autism, Dyslexia, CVA, and others, to focus on the
essential elements of the website more easily.
OFF ON
Keyboard Navigation (Motor) Use website with the keyboard
This profile enables motor-impaired persons to operate the website using the
keyboard Tab, Shift+Tab, and the Enter keys. Users can also use shortcuts such
as “M” (menus), “H” (headings), “F” (forms), “B” (buttons), and “G” (graphics)
to jump to specific elements.

Note: This profile prompts automatically for keyboard users.
OFF ON
Blind Users (Screen Reader) Optimize website for screen-readers
This profile adjusts the website to be compatible with screen-readers such as
JAWS, NVDA, VoiceOver, and TalkBack. A screen-reader is software that is
installed on the blind user’s computer and smartphone, and websites should
ensure compatibility with it.

Note: This profile prompts automatically to screen-readers.
Content Adjustments
Content Scaling
Default

Readable Font
Highlight Titles
Highlight Links
Text Magnifier
Adjust Font Sizing
Default

Align Center
Adjust Line Height
Default

Align Left
Adjust Letter Spacing
Default

Align Right
Color Adjustments
Dark Contrast
Light Contrast
High Contrast
High Saturation
Adjust Text Colors
Cancel
Monochrome
Adjust Title Colors
Cancel
Low Saturation
Adjust Background Colors
Cancel
Orientation Adjustments
Mute Sounds
Hide Images
Read Mode
Reading Guide
Useful Links
Select an option Home Header Footer Main Content
Stop Animations
Reading Mask
Highlight Hover
Highlight Focus
Big Black Cursor
Big White Cursor
HIDDEN_ADJUSTMENTS
Keyboard Navigation
Accessible Mode
Screen Reader Adjustments
Read Mode
Web Accessibility By
Learn More
Choose the Interface Language
English
Español
Deutsch
Português
Français
Italiano
עברית
繁體中文
Pусский
عربى
عربى
Nederlands
繁體中文
日本語
Polski
Türk
Accessibility StatementCompliance status

We firmly believe that the internet should be available and accessible to anyone
and are committed to providing a website that is accessible to the broadest
possible audience, regardless of ability.

To fulfill this, we aim to adhere as strictly as possible to the World Wide Web
Consortium’s (W3C) Web Content Accessibility Guidelines 2.1 (WCAG 2.1) at the AA
level. These guidelines explain how to make web content accessible to people
with a wide array of disabilities. Complying with those guidelines helps us
ensure that the website is accessible to blind people, people with motor
impairments, visual impairment, cognitive disabilities, and more.

This website utilizes various technologies that are meant to make it as
accessible as possible at all times. We utilize an accessibility interface that
allows persons with specific disabilities to adjust the website’s UI (user
interface) and design it to their personal needs.

Additionally, the website utilizes an AI-based application that runs in the
background and optimizes its accessibility level constantly. This application
remediates the website’s HTML, adapts its functionality and behavior for
screen-readers used by blind users, and for keyboard functions used by
individuals with motor impairments.

If you wish to contact the website’s owner please use the website's form

Screen-reader and keyboard navigation

Our website implements the ARIA attributes (Accessible Rich Internet
Applications) technique, alongside various behavioral changes, to ensure blind
users visiting with screen-readers can read, comprehend, and enjoy the website’s
functions. As soon as a user with a screen-reader enters your site, they
immediately receive a prompt to enter the Screen-Reader Profile so they can
browse and operate your site effectively. Here’s how our website covers some of
the most important screen-reader requirements:

 1. Screen-reader optimization: we run a process that learns the website’s
    components from top to bottom, to ensure ongoing compliance even when
    updating the website. In this process, we provide screen-readers with
    meaningful data using the ARIA set of attributes. For example, we provide
    accurate form labels; descriptions for actionable icons (social media icons,
    search icons, cart icons, etc.); validation guidance for form inputs;
    element roles such as buttons, menus, modal dialogues (popups), and others. 
    
    Additionally, the background process scans all of the website’s images. It
    provides an accurate and meaningful image-object-recognition-based
    description as an ALT (alternate text) tag for images that are not
    described. It will also extract texts embedded within the image using an OCR
    (optical character recognition) technology. To turn on screen-reader
    adjustments at any time, users need only to press the Alt+1 keyboard
    combination. Screen-reader users also get automatic announcements to turn
    the Screen-reader mode on as soon as they enter the website.
    
    These adjustments are compatible with popular screen readers such as JAWS,
    NVDA, VoiceOver, and TalkBack.
    
    
 2. Keyboard navigation optimization: The background process also adjusts the
    website’s HTML and adds various behaviors using JavaScript code to make the
    website operable by the keyboard. This includes the ability to navigate the
    website using the Tab and Shift+Tab keys, operate dropdowns with the arrow
    keys, close them with Esc, trigger buttons and links using the Enter key,
    navigate between radio and checkbox elements using the arrow keys, and fill
    them in with the Spacebar or Enter key.
    
    Additionally, keyboard users will find content-skip menus available at any
    time by clicking Alt+2, or as the first element of the site while navigating
    with the keyboard. The background process also handles triggered popups by
    moving the keyboard focus towards them as soon as they appear, not allowing
    the focus to drift outside.
    
    Users can also use shortcuts such as “M” (menus), “H” (headings), “F”
    (forms), “B” (buttons), and “G” (graphics) to jump to specific elements.

Disability profiles supported on our website
 * Epilepsy Safe Profile: this profile enables people with epilepsy to safely
   use the website by eliminating the risk of seizures resulting from flashing
   or blinking animations and risky color combinations.
 * Vision Impaired Profile: this profile adjusts the website so that it is
   accessible to the majority of visual impairments such as Degrading Eyesight,
   Tunnel Vision, Cataract, Glaucoma, and others.
 * Cognitive Disability Profile: this profile provides various assistive
   features to help users with cognitive disabilities such as Autism, Dyslexia,
   CVA, and others, to focus on the essential elements more easily.
 * ADHD Friendly Profile: this profile significantly reduces distractions and
   noise to help people with ADHD, and Neurodevelopmental disorders browse,
   read, and focus on the essential elements more easily.
 * Blind Users Profile (Screen-readers): this profile adjusts the website to be
   compatible with screen-readers such as JAWS, NVDA, VoiceOver, and TalkBack. A
   screen-reader is installed on the blind user’s computer, and this site is
   compatible with it.
 * Keyboard Navigation Profile (Motor-Impaired): this profile enables
   motor-impaired persons to operate the website using the keyboard Tab,
   Shift+Tab, and the Enter keys. Users can also use shortcuts such as “M”
   (menus), “H” (headings), “F” (forms), “B” (buttons), and “G” (graphics) to
   jump to specific elements.

Additional UI, design, and readability adjustments
 1. Font adjustments – users can increase and decrease its size, change its
    family (type), adjust the spacing, alignment, line height, and more.
 2. Color adjustments – users can select various color contrast profiles such as
    light, dark, inverted, and monochrome. Additionally, users can swap color
    schemes of titles, texts, and backgrounds with over seven different coloring
    options.
 3. Animations – epileptic users can stop all running animations with the click
    of a button. Animations controlled by the interface include videos, GIFs,
    and CSS flashing transitions.
 4. Content highlighting – users can choose to emphasize essential elements such
    as links and titles. They can also choose to highlight focused or hovered
    elements only.
 5. Audio muting – users with hearing devices may experience headaches or other
    issues due to automatic audio playing. This option lets users mute the
    entire website instantly.
 6. Cognitive disorders – we utilize a search engine linked to Wikipedia and
    Wiktionary, allowing people with cognitive disorders to decipher meanings of
    phrases, initials, slang, and others.
 7. Additional functions – we allow users to change cursor color and size, use a
    printing mode, enable a virtual keyboard, and many other functions.

Assistive technology and browser compatibility

We aim to support as many browsers and assistive technologies as possible, so
our users can choose the best fitting tools for them, with as few limitations as
possible. Therefore, we have worked very hard to be able to support all major
systems that comprise over 95% of the user market share, including Google
Chrome, Mozilla Firefox, Apple Safari, Opera and Microsoft Edge, JAWS, and NVDA
(screen readers), both for Windows and MAC users.

Notes, comments, and feedback

Despite our very best efforts to allow anybody to adjust the website to their
needs, there may still be pages or sections that are not fully accessible, are
in the process of becoming accessible, or are lacking an adequate technological
solution to make them accessible. Still, we are continually improving our
accessibility, adding, updating, improving its options and features, and
developing and adopting new technologies. All this is meant to reach the optimal
level of accessibility following technological advancements. If you wish to
contact the website’s owner, please use the website's form

Hide Accessibility Interface? Please note: If you choose to hide the
accessibility interface, you won't be able to see it anymore, unless you clear
your browsing history and data. Are you sure that you wish to hide the
interface?
Accept Cancel

Continue



Processing the data, please give it a few seconds...
Press Alt+1 for screen-reader mode