Privacy-Preserving
AI Technology
The most advanced and complete technology on the market to develop Artificial Intelligence with Data Privacy.
“Federated Learning accelerates model development while protecting privacy.”
“Federated Learning: A managed process for combining models trained separately on separate data sets that can be used for sharing intelligence between devices, systems, or firms to overcome privacy, bandwidth, or computational limits.“
While Federated Learning is a nascent technology, it is highly promising and can enable companies to realize transformative strategic business benefits. "FL is expected to make significant strides forward and transform enterprise business outcomes responsibly.”
“Federated Learning: AI's new weapon to ensure privacy.”
“Federated Learning allows AI algorithms to travel and train on distributed data that is retained by contributors. This technique has been used to train machine-learning algorithms to detect cancer in images that are retained in the databases of various hospital systems without revealing sensitive patient data.”
Federated
learning
After years of research, Sherpa.ai has develop the most advanced Federated Learning Platform for data privacy, which is making a huge impact on the academic world and industry.
Federated Learning is a Machine Learning paradigm aimed at learning models from decentralized data, such as data located in users’ smartphones, hospitals, or banks, and ensuring data privacy.
This is achieved by training models locally at each node (e.g. at each hospital, at each bank or at each smartphone), sharing the model-updated local parameters (without sharing user data) and securely aggregating them to build a better global model.
BENEFITS OF FEDERATED LEARNING
Companies are implementing Federated Learning as their data remains locked in their servers and only the predictive model with the knowledge acquired is transferred between parties.
More powerful collaborative models, or not feasible using standard solutions, without exchanging private data.
Data privacy by design, without risk of being compromised.
Regulation Compliance. The data never leaves the environment of the parties involved.
Lower risk of data breaches. The attack surface is reduced.
Transparency about how models are trained and how data is used.
Where to apply
Federated Learning
This technology is disruptive in cases where it is mandatory to guarantee data privacy.
When data contains confidential information, such as private patient data, personal financial information and any other confidential information.
Due to data privacy legislation, healthcare institutions, banks and insurance companies, for example, cannot share individual records, but would benefit from AI training in machine learning models from data from various entities.
Two parties want to take advantage of their data without sharing it. For example, two insurance companies could improve fraud detection, training models through federated learning, so that both companies would have a highly accurate predictive algorithm, but at no time would they share their business data with the other party.
Federated learning paradigms
Federated Learning can be classified into horizontal, vertical and federated transfer learning, according to how data is distributed among the agent nodes in the feature and sample spaces.
HORIZONTAL FEDERATED LEARNING
Horizontal Federated Learning is introduced in those scenarios, where data sets share the same feature space (same type of columns) but differ in samples (different rows).
Use cases: Diagnosis of diseases.
VERTICAL FEDERATED LEARNING
Two parties or companies want to take advantage of their data without sharing it. In this case, to perform the prediction, both parties need to have the same clients or users in common.
Use cases: Two insurance companies could improve fraud detection training models through federated learning so that both companies would have a highly accurate predictive algorithm, but they would not share their business data with the other party.
FEDERATED TRANSFER LEARNING
Two parties or companies want to take advantage of their data without sharing it but they only have very few clients of users in common.
The system can learn from common users and transfer de knowledge and apply it with news clients.
Use cases: Two insurance companies could improve fraud detection, training models through federated learning, so that both companies would have a highly accurate predictive algorithm, but they would not share their business data with the other party.
DIFFERENTIAL PRIVACY
ON TOP OF EVERYTHING
Differential Privacy is a statistical technique to provide data aggregations, while avoiding the leakage of individual data records. This technique ensures that malicious agents intervening in the communication of local parameters cannot trace this information back to the data sources, adding an additional layer of data privacy
FULLY INTERATED WITH
DIFFERENTIAL PRIVACY
NOISE ADDING MECHANISMS FOR
DIFFERENTIAL PRIVACY
- The Gaussian Mechanism which adds Gaussian noise is implemented in cases where accuracy maximization is what the model is aiming for
- The Laplace and Exponential Mechanisms are implemented in those models in which privacy preservation is the top priority.
- The Laplace and Gaussian mechanisms are focused on numerical answers in which noise is directly added to the answer itself. On the other hand, the Exponential Mechanism returns a precise answer without added noise, while still preserving Differential Privacy
This Federated Learning and Differential Privacy platform is highly flexible and scalable. Therefore, further Differentially Private mechanisms can be added.
ROBUST DEFENSE MECHANISMS
AGAINST ADVERSARIAL ATTACKS
DEFENSE AGAINST PRIVACY/INFERENCE ATTACKS
Federated Learning models, if not prevented, can be tricked into giving incorrect predictions and be able to give out any desired result. The process of designing an input in a specific way to obtain an incorrect result is an adversarial attack. These attacks are aimed at infering information from the training data.
DEFENSE AGAINST
DATA ATTACKS
The best way to check if a defense is satisfactory is to test it with different types of attacks. Therefore, a wide range of attacks have been designed in order to verify that the models are completely private.
DEFENSE AGAINST
MEMBERSHIP INFERENCE ATTACKS
While at all times meeting organizational requirements and guaranteeing data privacy, in accordance with current legislation.
DEFENSE AGAINST POISONING ATTACKS
Poisoning attacks pursue to compromise the global training model- Here, malicious users inject fake training data with the aim of corrupting the learned model. affecting the model’s performance and accuracy
DEFENSE AGAINST
BYZANTINE ATTACKS
With Sherpa.ai’s advanced mechanisms the defense of the federated model from malicious attacks aimed at reducing the model's performance is ensured. Therefore, the protection is based on the identification of those clients with anomalous performance in order to prevent them from participating in the aggregation process.
DEFENSE AGAINST BACKDOOR ATTACKS
Unprecedented algorithms capable of nullifying backdoor attacks have been established. With this technology, an increase of the performance and security of its models is achieved.
BIAS PREVENTION IN
FEDERATED LEARNING MODELS
BIAS PREVENTION
At Sherpa.ai we have developed a technology capable of tackling this problem, formed due to particularities of the data stored, and solving it in the most efficient way possible. To do this, we adjust, particularize and adapt each model to each client while preserving global learning.
PREVENTING BIAS THROUGH
PERSONALIZATION
This is achieved by dynamically modifying the device loss functions in each learning round, so that the resulting model is unbiased towards any user.
Other technological aspects
of sherpa.ai´s privacy-preserving technology
Secure Multi-Party
Computation
By doing this, it is ensured that your business’s sensitive data is secured, without undercutting your ability to acquire all the necessary information needed from this data.
Private Entity
Resolution
With the use of cutting edge cryptographic techniques, the synchronization and identification of these datasets is possible while always protecting privacy and never affecting the performance of the trained models.
SYNTHETIC DATA GENERATION
Sherpa.ai’s technology makes use of advanced synthetic data generation to eliminate security loopholes such as membership. With this unconventional solution, the ability to move away from the use of standard methods is gained, which greatly reduces communication costs without degrading the accuracy of the predictive model. This generates the ability to obtain the underlying structure and show the same statistical distribution from the original data, rendering it undistinguishable from the real one.
Compliance
Privacy
Data privacy is a fundamental ethical value at Sherpa.ai.
Our platform complies with all current regulations on Data Protection (GDPR) and is in line with the European Commission regulatory framework proposal on Artificial Intelligence.
Security
Information security is a top priority at Sherpa.ai.
We believe that security must comply with quality standards and with all regulations in this regard. For this reason, we are certified in the ISO-27.001 data security standard and our platform has won the CogX 2021 awards for its Outstanding Contribution to Technology Regulation and has been a finalist as Best Solution for Privacy and Data Protection.
CONTACT SHERPA.AI
Take the lead in your sector and be more competitive.
Write us and let's talk about Privacy-Preserving Artificial Intelligence to scale your business.
QUOTES
FROM OUR TEAM
We have reached the highest levels in the implementation of algorithms for the Artificial Intelligence platform with data privacy of Sherpa.ai, with the most advanced methodologies of applied mathematics
Enrique Zuazua, Ph.D.
Senior Associate Researcher in Algorithms of Sherpa.ai
Sherpa is leading the way how artificial intelligence solutions will be built, preserving user privacy in all its forms
Tom Gruber
Senior Advisor in AI of Sherpa.ai