Szilvia Lestyán
Research assistant
lestyan (at) crysys.hu
web: www.crysys.hu/~lestyan/
office: I.E. 429
tel: +36 1 463 2063
Current courses | Student projects | Publications
Short Bio
Szilvia obtained both her MSc and BSc diplomas in Applied Mathematics at the Eötvös Loránd University (Hungary), where she specialized in computer science. She has been doing research in the CrySyS Lab. under the guidance of Dr Gergely Ács and Dr. Gergely Biczók since 2017.
Current Courses
IT Security Laboratory (VIHIMB01)
This laboratory extends and deepens the knowledge and skills obtained in the courses of the IT Security minor specialization by solving practical, hands-on exercises in real, or close-to-real environments.
Security in Machine Learning (VIHIAV45)
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake. Such an example is when the input image clearly pictures a school bus, but the model identifies it as an ostrich. This course provides a detailed overview of the security of machine learning systems. It focuses on attack and defense techniques and the theoretical background mainly of adversarial examples.
Student Project Proposals
Security and Privacy in/with Machine Learning
Machine Learning (Artificial Intelligence) has become undisputedly popular in recent years. The number of security critical applications
of machine learning has been steadily increasing over the years (self-driving cars, user authentication, decision support, profiling, risk assessment, etc.).
However, there are still many open privacy and security problems of machine learning. Students can work on the following topics:
- Own idea: If you have any own project idea related to data privacy, or the security/privacy of machine learning, and I find it interesting, you can work on that under my guidance... You'll get +1 grade in that case. (Contact: Gergely Acs)
- Robustness, adversarial examples: Adversarial examples are maliciously modified samples where the modification is visually imperceptible yet the prediction of the model on this slightly modified sample is very different compared to the unmodified sample. A potential task can be to develop solutions to distinguish adversarial and benign samples, or to develop robust training algorithms. (Contact: Szilvia Lestyán, Gergely Acs)
- Watermarking of Machine Learning models: As model extraction is easy (i.e., one can easily steal a machine learning by using it as an oracle), model owners embed a watermark into the trained model and claim ownership upon a copyright dispute in order to discourage model extraction. Watermarks can be implemented by inserting a backdoor sample into the model that is only known to the model owner. A potential task can be to develop, evaluate (compare) watermarking schemes. (Contact: Gergely Ács)
- Record reconstruction from aggregate queries: It is (falsely) believed that aggregation preserves privacy, that is, if one computes several aggregation queries (SUM, AVG, COUNT, etc.) on a database then it is very hard to infer the individual record values in the table only from these aggregates. A potential task can be to implement attacks which check whether a set of aggregate queries can be answered without revealing any single individual record on which these queries were computed. (Contact: Gergely Ács)
- Anonymization: Sequential data includes any data where data records contain the sequence of items of a user (e.g., location trajectories, time-series data such as electricity consumption, browsing history, etc.). A potential task can be to develop (GDPR compliant) anonymization methods so that individuals are not re-identifiable anymore in the dataset. (Contact: Gergely Ács)
- Fairness vs. privacy vs. robustness in Machine Learning: In machine learning, privacy-preserving training is considered unfair to subgroups as the trained model is less accurate on underrepresented groups (e.g., minorities). It is an open question how privacy-preservation and fairness together influence robustness (i.e., resistance against integrity attacks such as poisoning or adversarial examples). A potential task can be to study the relation of privacy-preservation, fairness, and robustness in machine learning. (Contact: Gergely Ács)
- Other Topics: For details, click HERE! (Contact: Balázs Pejó)
Required skills: none
Preferred skills: basic programming skills (e.g., python), machine learning (not required)
Publications
2022
In search of lost utility: private location data
Sz. Lestyán, G. Ács, G. Biczók
Privacy Enhancing Technologies Symposium (PETS), 2022.
Bibtex | Abstract | PDF | Link
@conference {
author = {Szilvia Lestyan, Gergely Ács, Gergely Biczók},
title = {In search of lost utility: private location data},
booktitle = {Privacy Enhancing Technologies Symposium (PETS)},
year = {2022},
howpublished = "\url{https://arxiv.org/pdf/2008.01665.pdf}"
}
Keywords
Location data anonymization, Differential Privacy, Generative ModelsAbstract
The unavailability of training data is a permanent source of much frustration in research, especially when it is due to privacy concerns. This is particularly true for location data since previous techniques all suffer from the inherent sparseness and high dimensionality of location trajectories which render most techniques impractical, resulting in unrealistic traces and unscalable methods. Moreover, time information of location visits is usually dropped, or its resolution is drastically reduced. In this paper we present a novel technique for privately releasing a composite generative model and whole high-dimensional location datasets with detailed time information. To generate high-fidelity synthetic data, we leverage several peculiarities of vehicular mobility such as its language-like characteristics ("you should know a location by the company it keeps") or how humans plan their trips from one point to the other. We model the generator distribution of the dataset by first constructing a variational autoencoder to generate the source and destination locations, and the corresponding timing of trajectories. Next, we compute transition probabilities between locations with a feed forward network, and build a transition graph from the output of this model, which approximates the distribution of all paths between the source and destination (at a given time). Finally, a path is sampled from this distribution with a Markov Chain Monte Carlo method. The generated synthetic dataset is highly realistic, scalable, provides good utility and, nonetheless, provably private. We evaluate our model against two state-of-the-art methods and three real-life datasets demonstrating the benefits of our approach.2021
Privacy of Aggregated Mobility Data
G. Ács, Sz. Lestyán, G. Biczók
Jajodia S., Samarati P., Yung M. (eds) Encyclopedia of Cryptography, Security and Privacy. Springer, Berlin, Heidelberg., Springer, 2021.
@inproceedings {
author = {Gergely Ács, Szilvia Lestyan, Gergely Biczók},
title = {Privacy of Aggregated Mobility Data},
booktitle = {Jajodia S., Samarati P., Yung M. (eds) Encyclopedia of Cryptography, Security and Privacy. Springer, Berlin, Heidelberg.},
publisher = {Springer},
year = {2021},
howpublished = "\url{https://doi.org/10.1007/978-3-642-27739-9_1575-1}"
}
Abstract
2019
Automatic Driver Identification from In-Vehicle Network Logs
M. Remeli, Sz. Lestyán, G. Ács, G. Biczók
22th IEEE Intelligent Transportation Systems Conference (ITSC), IEEE, 2019.
@inproceedings {
author = {Mina Remeli, Szilvia Lestyan, Gergely Ács, Gergely Biczók},
title = {Automatic Driver Identification from In-Vehicle Network Logs},
booktitle = {22th IEEE Intelligent Transportation Systems Conference (ITSC)},
publisher = {IEEE},
year = {2019},
howpublished = "\url{https://arxiv.org/pdf/1911.09508.pdf}"
}
Abstract
Extracting vehicle sensor signals from CAN logs for driver re-identification
Sz. Lestyán, G. Ács, G. Biczók, Zs. Szalay
5th International Conference on Information Security and Privacy (ICISSP 2019), SCITEPRESS, 2019, shortlisted for Best Student Paper Award.
@inproceedings {
author = {Szilvia Lestyan, Gergely Ács, Gergely Biczók, Zsolt Szalay},
title = {Extracting vehicle sensor signals from CAN logs for driver re-identification},
booktitle = {5th International Conference on Information Security and Privacy (ICISSP 2019)},
publisher = {SCITEPRESS},
year = {2019},
note = {shortlisted for Best Student Paper Award}
}
Abstract
Data is the new oil for the car industry. Cars generate data about how they are used and who’s behind the wheel which gives rise to a novel way of profiling individuals. Several prior works have successfully demonstrated the feasibility of driver re-identification using the in-vehicle network data captured on the vehicle’s CAN bus. However, all of them used signals (e.g., velocity, brake pedal or accelerator position) that have already been extracted from the CAN log which is itself not a straightforward process. Indeed, car manufacturers intentionally do not reveal the exact signal location within CAN logs. Nevertheless, we show that signals can be efficiently extracted from CAN logs using machine learning techniques. We exploit that signals have several distinguishing statistical features which can be learnt and effectively used to identify them across different vehicles, that is, to quasi ”reverse-engineer” the CAN protocol. We also demonstrate that the extracted signals can be successfully used to re-identify individuals in a dataset of 33 drivers. Therefore, hiding signal locations in CAN logs per se does not prevent them to be regarded as personal data of drivers.2016
Privacy Preserving Data Aggregation over Multi-hop Networks
Sz. Lestyán
Infocommunications Journal, pp. 7-15, December 2016, Volume VIII, Number 4, ISSN 2061-2079, 2016.
@article {
author = {Szilvia Lestyan},
title = {Privacy Preserving Data Aggregation over Multi-hop Networks},
journal = {Infocommunications Journal, pp. 7-15, December 2016, Volume VIII, Number 4, ISSN 2061-2079},
year = {2016}
}
Abstract
2014
Efficient Apriori Based Algorithms for Privacy Preserving Frequent Itemset Mining
Sz. Lestyán, A. Csiszárik, A. Lukács
Cognitive Infocommunications (CogInfoCom), 2014 5th IEEE Conference on Cognitive Infocommunications, 2014.
@article {
author = {Szilvia Lestyan, Adrián Csiszárik, András Lukács},
title = {Efficient Apriori Based Algorithms for Privacy Preserving Frequent Itemset Mining},
journal = {Cognitive Infocommunications (CogInfoCom), 2014 5th IEEE Conference on Cognitive Infocommunications},
year = {2014}
}