PRIMAL · Private Machine Learning
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2020-06-01 → 2024-02-28
- EU contribution
- €185,464
- Participants
- 1
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
Private Machine Learning
The primary focus of this research is on improving techniques for secure multi-party computation (MPC). Secure multi-party computation involves computationally distrustful parties wishing to jointly compute a function while protecting the privacy of their individual inputs. This allows the computation of sensitive data without disclosing it. MPC allows designing cryptographic solutions that, for instance, enable querying a remote database without revealing the query to the server, enhance anonymity over the internet, or allow medical research on genomics across organizations without disclosing the patients’ DNA. The development of secure computation techniques will allow better protection of the privacy of individuals. The primary objective of this research is to develop privacy-preserving techniques with an emphasis on applications in machine-learning algorithms and data mining. Our results, however, evolved to prioritize foundational work on privacy-preserving techniques with broader applicability beyond machine learning. Our research encompasses a diverse spectrum, delving into fundamental aspects of secure computation and drawing insights from disciplines such as algorithms, data structures, and distributed computing.
Data: CORDIS, © European Union
Project objective
Machine learning algorithms are data-hungry, and perform better when exposed to more and more data. Such data is being collected in massive amounts by internet giants, and is often sensitive and private. Examples include the purchases and browsing history of users, their health data and exercise activity, locations they travel to and messages they type into their mobile phone. The amount of data being collected can be significantly reduced using cryptographic techniques, in particular, using secure multiparty computation. Secure computation enables mutually distrustful parties to compute a joint function of their inputs without revealing the inputs to one another. In this research, we will address secure computation techniques of machine learning tasks. The first task is private classification: One party holds a model trained on a sensitive dataset, and another party holds a sample and wishes to evaluate the model on that private sample. Our objective is to fulfill this task while achieving significantly stronger security notion than previous works, that is, security even if one of the parties deviates from the protocol specifications (malicious security). The second task is federated learning, a techniques that enables thousands of participants to train a neural network on their joint data but without revealing the data to one another. However, a recent work showed that such task is susceptible to injection of backdoors, and a user can manipulate the joint model to his/her own benefit, significantly reducing the usefulness of federated learning in practice. Our objective is to guarantee immunity to such injections. The two objectives will be achieved by improving specific cryptographic building blocks, and applying them for these applications. PRIMAL will speed up secure computation in practice, and carries immense potential to enhance privacy in the digital era.
Original text from CORDIS.
Participants
- BAR ILAN UNIVERSITY · Ramat GanCoordinatorIsrael
Links
Data: CORDIS, © European Union