A5000583679- Cryptography and Data Security
- Privacy-Preserving Technologies in Data
- Stochastic Gradient Optimization Techniques
- Adversarial Robustness in Machine Learning
- Coding theory and cryptography
- Complexity and Algorithms in Graphs
- Cryptographic Implementations and Security
- Biometric Identification and Security
- Genomic variations and chromosomal abnormalities
- Cancer Genomics and Diagnostics
- Advanced Malware Detection Techniques
- Face and Expression Recognition
- Machine Learning in Healthcare
- Cloud Data Security Solutions
- Cybercrime and Law Enforcement Studies
- Random Matrices and Applications
- Oral and gingival health research
- Forensic and Genetic Research
- Information and Cyber Security
Broad Institute
2023
École Polytechnique Fédérale de Lausanne
2020-2021
Furthermore, the trusted party becomes a single point of failure, thus both data and model privacy could be compromised by breaches, hacking, leaks, etc.Hence, solutions originating from cryptographic community replace emulate with group computing servers.In particular, to enable privacy-preserving training NNs, several studies employ multiparty computation (MPC) techniques operate on two [83], [28], three [82], [110],[111], or four [26], [27] server models.Such approaches, however, limit...
Fully Homomorphic Encryption (FHE) is a cryptographic primitive that allows performing arbitrary operations on encrypted data. Since the conception of idea in [RAD78], it has been considered holy grail cryptography. After first construction 2009 [Gen09], evolved to become practical with strong security guarantees. Most modern constructions are based well-known lattice problems such as Learning With Errors (LWE). Besides its academic appeal, recent years FHE also attracted significant...
Abstract We propose and evaluate a secure-multiparty-computation (MPC) solution in the semi-honest model with dishonest majority that is based on multiparty homomorphic encryption (MHE). To support our solution, we introduce version of Brakerski-Fan-Vercauteren cryptosystem implement it an open-source library. MHE-based MPC solutions have several advantages: Their transcript public, their o~ine phase compact, circuit-evaluation procedure noninteractive. By exploiting these properties,...
Genotype imputation is a fundamental step in genomic data analysis, where missing variant genotypes are predicted using the existing of nearby "tag" variants. Although researchers can outsource genotype imputation, privacy concerns may prohibit genetic sharing with an untrusted service. Here, we developed secure efficient homomorphic encryption (HE) techniques. In HE-based methods, while it transit, at rest, and analysis. It only be decrypted by owner. We compared three state-of-the-art...
Abstract In this paper, we address the problem of privacy-preserving distributed learning and evaluation machine-learning models by analyzing it in widespread MapReduce abstraction that extend with privacy constraints. We design spindle (Scalable Privacy-preservINg Distributed LEarning), first system covers complete ML workflow enabling execution a cooperative gradient-descent obtained model preserving data confidentiality passive-adversary up to N −1 colluding parties. uses multiparty...
Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the problem of performing a federated PCA on private distributed among multiple providers while ensuring confidentiality. Our solution, SF-PCA, end-to-end secure system that preserves confidentiality both original and all intermediate results passive-adversary model with up to all-but-one colluding parties. SF-PCA jointly leverages multiparty homomorphic...
Training accurate and robust machine learning models requires a large amount of data that is usually scattered across silos. Sharing or centralizing the different healthcare institutions is, however, unfeasible prohibitively difficult due to privacy regulations. In this work, we address problem by using privacy-preserving federated learning-based approach, PriCell, for complex such as convolutional neural networks. PriCell relies on multiparty homomorphic encryption enables collaborative...
ABSTRACT Genotype imputation is a fundamental step in genomic data analysis such as GWAS, where missing variant genotypes are predicted using the existing of nearby ‘tag’ variants. Imputation greatly decreases genotyping cost and provides high-quality estimates common genotypes. As population panels increase, e.g., TOPMED Project, genotype becoming more accurate, but it requires high computational power. Although researchers can outsource imputation, privacy concerns may prohibit genetic...
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in cross-silo federated learning setting by relying multiparty homomorphic encryption. RHODE preserves the confidentiality data, model, data; it mitigates attacks target gradients under passive-adversary threat model. propose packing scheme, multi-dimensional packing, for better utilization Single Instruction, Multiple Data (SIMD) operations With efficient...
ABSTRACT Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data-silos. Sharing or centralizing the different healthcare institutions is, however, unfeasible prohibitively difficult due to privacy regulations. In this work, we address problem by using novel privacy-preserving federated learning-based approach, PriCell , for complex such as convolutional neural networks. relies on multiparty homomorphic encryption enables...
Cyber Threat Intelligence (CTI) sharing is an important activity to reduce information asymmetries between attackers and defenders. However, this presents challenges due the tension data confidentiality, that result in retention often leading a free-rider problem. Therefore, shared represents only tip of iceberg. Current literature assumes access centralized databases containing all information, but not always feasible, aforementioned tension. This results unbalanced or incomplete datasets,...
Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the problem of performing a federated PCA on private distributed among multiple providers while ensuring confidentiality. Our solution, SF-PCA, end-to-end secure system that preserves confidentiality both original and all intermediate results passive-adversary model with up to all-but-one colluding parties. SF-PCA jointly leverages multiparty homomorphic...
Homomorphic encryption (HE), which allows computations on encrypted data, is an enabling technology for confidential cloud computing. One notable example privacy-preserving Prediction-as-a-Service (PaaS), where machine-learning predictions are computed data. However, developing HE-based solutions PaaS a tedious task requires careful design that predominantly depends the deployment scenario and leveraging characteristics of modern HE schemes. Prior works focus solely protecting...
In this paper, we address the problem of privacy-preserving training and evaluation neural networks in an $N$-party, federated learning setting. We propose a novel system, POSEIDON, first its kind regime network training. It employs multiparty lattice-based cryptography to preserve confidentiality data, model, under passive-adversary model collusions between up $N-1$ parties. To efficiently execute secure backpropagation algorithm for networks, provide generic packing approach that enables...
In this paper, we address the problem of privacy-preserving distributed learning and evaluation machine-learning models by analyzing it in widespread MapReduce abstraction that extend with privacy constraints. We design SPINDLE (Scalable Privacy-preservINg Distributed LEarning), first system covers complete ML workflow enabling execution a cooperative gradient-descent obtained model preserving data confidentiality passive-adversary up to N-1 colluding parties. uses multiparty homomorphic...
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in cross-silo federated learning setting by relying multiparty homomorphic encryption. RHODE preserves the confidentiality data, model, data; it mitigates attacks target gradients under passive-adversary threat model. propose packing scheme, multi-dimensional packing, for better utilization Single Instruction, Multiple Data (SIMD) operations With efficient...