Sven Laur

Sven Laur


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 August 2021 in Cryptography
Verified
Journal Article
Open access
PDF file
AOAndre Ostrak
Andre Ostrak
JRJaak Randmets
Jaak Randmets
VSVille Sokk
Ville Sokk
SLSven Laur
Sven Laur
LKLiina Kamm
Liina Kamm
In bioinformatics, genome-wide association studies (GWAS) are used to detect associations between single-nucleotide polymorphisms (SNPs) and phenotypic traits such as diseases. Significant differences in SNP counts between case and control groups can signal association between variants and phenotypic traits. Most traits are affected by multiple genetic locations. To detect these subtle associations, bioinformaticians need access to more heterogeneous data. Regulatory restrictions in cross-border health data exchange have created a surge in research on privacy-preserving solutions, including secure computing techniques. However, in studies of such scale, one must account for population stratification, as under- and over-representation of sub-populations can lead to spurious associations. We improve on the state of the art of privacy-preserving GWAS methods by showing how to adapt principal component analysis (PCA) with stratification control (EIGENSTRAT), FastPCA, EMMAX and the genomic control algorithm for secure computing. We implement these methods using secure computing techniques—secure multi-party computation (MPC) and trusted execution environments (TEE). Our algorithms are the most complex ones at this scale implemented with MPC. We present performance benchmarks and a security and feasibility trade-off discussion for both techniques.

15 February 2013 in BMC Genomics
Verified
Journal Article
Open access
PDF file
KTKonstantin Tretyakov
Konstantin Tretyakov
SLSven Laur
Sven Laur
GSGeert Smant
Geert Smant
JVJaak Vilo
Jaak Vilo
PPPjotr Prins
Pjotr Prins
Biological data acquisition is raising new challenges, both in data analysis and handling. Not only is it proving hard to analyze the data at the rate it is generated today, but simply reading and transferring data files can be prohibitively slow due to their size. This primarily concerns logistics within and between data centers, but is also important for workstation users in the analysis phase. Common usage patterns, such as comparing and transferring files, are proving computationally expensive and are tying down shared resources.

18 May 2023
Verified
Book Chapter
Open access
PDF file
HŠHendrik Šuvalov
Hendrik Šuvalov
SLSven Laur
Sven Laur
RKRaivo Kolde
Raivo Kolde
Neural network language models, such as BERT, can be used for information extraction from medical texts with unstructured free text. These models can be pre-trained on a large corpus to learn the language and characteristics of the relevant domain and then fine-tuned with labeled data for a specific task. We propose a pipeline using human-in-the-loop labeling to create annotated data for Estonian healthcare information extraction. This method is particularly useful for low-resource languages and is more accessible to those in the medical field than rule-based methods like regular expressions.

21 August 2021 in Cryptography
Verified
Journal Article
Open access
PDF file
SLSven Laur
Sven Laur
PPPille Pullonen
Pille Pullonen
This paper formalises the security of programmable secure computation focusing on simplifying security proofs of new algorithms for existing computation frameworks. Security of the frameworks is usually well established but the security proofs of the algorithms are often more intuitive than rigorous. This work specifies a transformation from the usual hybrid execution model to an abstract model that is closer to the intuition. We establish various preconditions that are satisfied by natural secure computation frameworks and protocols, thus showing that mostly the intuitive proofs suffice. More elaborate protocols might still need additional proof details.

16 February 2023 in medRxiv
Verified
Preprint
Open access
PDF file
MOMarek Oja
Marek Oja
STSirli Tamm
Sirli Tamm
KMKerli Mooses
Kerli Mooses
MPMaarja Pajusalu
Maarja Pajusalu
HTHarry-Anton Talvik
Harry-Anton Talvik
SRSulev Reisberg
Sulev Reisberg
Objective: To describe the reusable transformation process of electronic health records (EHR), claims, and prescriptions data into Observational Medical Outcome Partnership (OMOP) common data model (CDM), together with challenges faced and solutions implemented. Materials and Methods: We used Estonian national health databases that store almost all residents' claims, prescriptions, and EHR records. To develop and demonstrate the transformation process of Estonian health data to OMOP CDM, we used a 10% random sample of the Estonian population (n = 150,824 patients) from 2012-2019. For the sample, complete information from all three databases was converted to OMOP CDM version 5.3. The validation was performed using open-source tools. Results: In total, we transformed over 100 million entries to standard concepts using standard OMOP vocabularies with the average mapping rate 95%. For conditions, observations, drugs, and measurements, the mapping rate was over 90%. In most cases, SNOMED Clinical Terms were used as the target vocabulary. Discussion: During the transformation process, we encountered several challenges, which are described in detail with concrete examples and solutions. Conclusion: For a representative 10% random sample, we successfully transferred complete records from three national health databases to OMOP CDM and created a reusable transformation process. Our work helps future researchers to transform linked databases into OMOP CDM more efficiently, ultimately leading to better real-world evidence.

1 January 2026 in IET Information Security
Verified
Journal Article
Open access
AHAnette Habanen
Anette Habanen
JWJan Willemson
Jan Willemson
SLSven Laur
Sven Laur
The recent rise of artificial intelligence (AI) solutions has also had a significant impact on electoral processes. Most notably, deepfakes created by generative AI applications can (and have been) used to spread misinformation during the campaigns, but they can also be used for cyberattack automation, biased social media bots, etc. We instead present a positive use case for generative AI in manipulating video material required as proof of voting by potential coercers. For this, we have created a pipeline that takes a video of a voting ballot and replaces its critical content (in our case, the digits on the ballot). To achieve this, a YOLOv11 model is used to find the digits, a WavePaint image inpainting model is used to cover up the old digits and a separate image of the new digits is used to place them into the video. Additionally, we implemented the prototype application in the form of a web service and validated the outcome by asking the humans to distinguish fake ballot images and videos from the real ones. Our results show that humans can still recognise fake ballot videos relatively well, implying that requesting ballot videos is still an efficient attack against voter freedom in the case of paper voting. However, future developments in the generative AI techniques are likely to improve the situation significantly.