Lucas Lange

selected publications

1. Slice It up: Unmasking User Identities in Smartwatch Health Data

   Lucas Lange, Tobias Schreieder, Victor Christen, and Erhard Rahm

   20th ACM ASIA Conference on Computer and Communications Security (AsiaCCS 2025) [accepted] (Aug. 2025)

   Abs Bib Pub PDF Code

   Wearables are widely used for health data collection due to their availability and advanced sensors, enabling smart health applications like stress detection. However, the sensitivity of personal health data raises significant privacy concerns. While user de-identification by removing direct identifiers such as names and addresses is commonly employed to protect privacy, the data itself can still be exploited to re-identify individuals. We introduce a novel framework for similarity-based Dynamic Time Warping (DTW) re-identification attacks on time series health data. Using the WESAD dataset and two larger synthetic datasets, we demonstrate that even short segments of sensor data can achieve perfect re-identification with our Slicing-DTW-Attack. Our attack is independent of training data and computes similarity rankings in about 2 minutes for 10,000 subjects on a single CPU core. These findings highlight that de-identification alone is insufficient to protect privacy. As a defense, we show that adding random noise to the signals significantly reduces re-identification risk while only moderately affecting usability in stress detection tasks, offering a promising approach to balancing privacy and utility.

   @inproceedings{langeSliceItUnmasking2025,
     title = {Slice It up: {{Unmasking User Identities}} in {{Smartwatch Health Data}}},
     author = {Lange, Lucas and Schreieder, Tobias and Christen, Victor and Rahm, Erhard},
     year = {2025},
     month = aug,
     booktitle = {20th ACM ASIA Conference on Computer and Communications Security (AsiaCCS 2025) [accepted]},
     doi = {10.48550/arXiv.2308.08310},
     url = {http://arxiv.org/abs/2308.08310},
     urldate = {2023-10-17},
     code = {https://github.com/tobiasschreieder/dtw-attacks},
     pdf = {https://arxiv.org/pdf/2308.08310.pdf},
     bibtexshow = {false},
     selected = {true}
   }

2. Federated Learning With Individualized Privacy Through Client Sampling

   Lucas Lange, Ole Borchardt, and Erhard Rahm

   10th International Conference on Machine Learning Technologies (ICMLT 2025) [accepted] (May. 2025)

   Abs Bib Pub PDF Code

   With growing concerns about user data collection, individualized privacy has emerged as a promising solution to balance protection and utility by accounting for diverse user privacy preferences. Instead of enforcing a uniform level of anonymization for all users, this approach allows individuals to choose privacy settings that align with their comfort levels. Building on this idea, we propose an adapted method for enabling Individualized Differential Privacy (IDP) in Federated Learning (FL) by handling clients according to their personal privacy preferences. By extending the SAMPLE algorithm from centralized settings to FL, we calculate client-specific sampling rates based on their heterogeneous privacy budgets and integrate them into a modified IDP-FedAvg algorithm. We test this method under realistic privacy distributions and multiple datasets. The experimental results demonstrate that our approach achieves clear improvements over uniform DP baselines, reducing the trade-off between privacy and utility. Compared to the alternative SCALE method in related work, which assigns differing noise scales to clients, our method performs notably better. However, challenges remain for complex tasks with non-i.i.d. data, primarily stemming from the constraints of the decentralized setting.

   @inproceedings{langeFederatedLearningIndividualized2025,
     title = {Federated {{Learning With Individualized Privacy Through Client Sampling}}},
     author = {Lange, Lucas and Borchardt, Ole and Rahm, Erhard},
     year = {2025},
     month = may,
     booktitle = {10th International Conference on Machine Learning Technologies (ICMLT 2025) [accepted]},
     doi = {10.48550/arXiv.2501.17634},
     url = {http://arxiv.org/abs/2501.17634},
     urldate = {2025-01-30},
     keywords = {Computer Science - Computer Vision and Pattern Recognition,Computer Science - Cryptography and Security,Computer Science - Machine Learning},
     code = {https://github.com/luckyos-code/flidp},
     pdf = {http://arxiv.org/pdf/2501.17634.pdf},
     bibtexshow = {false},
     selected = {true}
   }

3. Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning

   Lucas Lange, Maurice-Maximilian Heykeroth, and Erhard Rahm

   21st Conference on Database Systems for Business, Technology and Web (BTW 2025) (May. 2025)

   Abs Bib Pub PDF Code

   Machine Learning (ML) is crucial in many sectors, including computer vision. However, ML models trained on sensitive data face security challenges, as they can be attacked and leak information. Privacy-Preserving Machine Learning (PPML) addresses this by using Differential Privacy (DP) to balance utility and privacy. This study identifies image dataset characteristics that affect the utility and vulnerability of private and non-private Convolutional Neural Network (CNN) models. Through analyzing multiple datasets and privacy budgets, we find that imbalanced datasets increase vulnerability in minority classes, but DP mitigates this issue. Datasets with fewer classes improve both model utility and privacy, while high entropy or low Fisher Discriminant Ratio (FDR) datasets deteriorate the utility-privacy trade-off. These insights offer valuable guidance for practitioners and researchers in estimating and optimizing the utility-privacy trade-off in image datasets, helping to inform data and privacy modifications for better outcomes based on dataset characteristics.

   @inproceedings{langeAssessingImpactImage2025,
     title = {Assessing the {{Impact}} of {{Image Dataset Features}} on {{Privacy-Preserving Machine Learning}}},
     booktitle = {21st {{Conference}} on {{Database Systems}} for {{Business}}, {{Technology}} and {{Web}} ({{BTW}} 2025)},
     author = {Lange, Lucas and Heykeroth, Maurice-Maximilian and Rahm, Erhard},
     year = {2025},
     pages = {589--612},
     publisher = {Gesellschaft f{\"u}r Informatik, Bonn},
     url = {https://dl.gi.de/handle/20.500.12116/45890},
     urldate = {2025-03-06},
     langid = {english},
     code = {https://github.com/luckyos-code/dataset-analysis-ppml},
     pdf = {https://dl.gi.de/server/api/core/bitstreams/cc5101ff-d3e8-4c5b-a466-896180a8f24f/content},
     bibtexshow = {true},
     selected = {true}
   }