Johannes Liebenow
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Johannes Liebenow has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Esfandiar Mohammadi
Institute for IT Security University of Luebeck Luebeck Germany
4 shared publications - Marcel Gehrke
University of Hamburg
2 shared publications - Tanya Braun
University of Munster
2 shared publications - Florian Thaeter
Independent, Vancover, Canada
1 shared publication - Jan Rupp
University of Lübeck
1 shared publication - Marcel Heisel
Institute for IT-Security, University of Lübeck, Lübeck, Germany
1 shared publication
Latest Publications
- Open Access
DP-HYPE: Distributed Differentially Private Hyperparameter Search
The tuning of hyperparameters in distributed machine learning can substantially impact model performance. When the hyperparameters are tuned on sensitive data, privacy becomes an important challenge and to this end, differential privacy has emerged as the de facto standard for provable privacy. A standard setting when performing distributed learning tasks is that clients agree on a shared setup, i.e., find a compromise from a set of hyperparameters, like the learning rate of the model to be trained. Yet, prior work on differentially private hyperparameter tuning either uses computationally expensive cryptographic protocols, determines hyperparameters separately for each client, or applies differential privacy locally, which can lead to undesirable utility-privacy trade-offs. In this work, we present our algorithm DP-HYPE, which performs a distributed and privacy-preserving hyperparameter search by conducting a distributed voting based on local hyperparameter evaluations of clients. In this way, DP-HYPE selects hyperparameters that lead to a compromise supported by the majority of clients, while maintaining scalability and independence from specific learning tasks. We prove that DP-HYPE preserves the strong notion of differential privacy called client-level differential privacy and, importantly, show that its privacy guarantees do not depend on the number of hyperparameters. We also provide bounds on its utility guarantees, that is, the probability of reaching a compromise, and implement DP-HYPE as a submodule in the popular Flower framework for distributed machine learning. In addition, we evaluate performance on multiple benchmark data sets in iid as well as multiple non-iid settings and demonstrate high utility of DP-HYPE even under small privacy budgets.
Open AccessDP-HYPE: Distributed Differentially Private Hyperparameter Search
The tuning of hyperparameters in distributed machine learning can substantially impact model performance. When the hyperparameters are tuned on sensitive data, privacy becomes an important challenge and to this end, differential privacy has emerged as the de facto standard for provable privacy. A standard setting when performing distributed learning tasks is that clients agree on a shared setup, i.e., find a compromise from a set of hyperparameters, like the learning rate of the model to be trained. Yet, prior work on differentially private hyperparameter tuning either uses computationally expensive cryptographic protocols, determines hyperparameters separately for each client, or applies differential privacy locally, which can lead to undesirable utility-privacy trade-offs. In this work, we present our algorithm DP-HYPE, which performs a distributed and privacy-preserving hyperparameter search by conducting a distributed voting based on local hyperparameter evaluations of clients. In this way, DP-HYPE selects hyperparameters that lead to a compromise supported by the majority of clients, while maintaining scalability and independence from specific learning tasks. We prove that DP-HYPE preserves the strong notion of differential privacy called client-level differential privacy and, importantly, show that its privacy guarantees do not depend on the number of hyperparameters. We also provide bounds on its utility guarantees, that is, the probability of reaching a compromise, and implement DP-HYPE as a submodule in the popular Flower framework for distributed machine learning. In addition, we evaluate performance on multiple benchmark data sets in iid as well as multiple non-iid settings and demonstrate high utility of DP-HYPE even under small privacy budgets.
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 273-287
DPM: Clustering Sensitive Data through Separation
Clustering is an important tool for data exploration where the goal is to subdivide a data set into disjoint clusters that fit well into the underlying data structure. When dealing with sensitive data, privacy-preserving algorithms aim to approximate the non-private baseline while minimising the leakage of sensitive information. State-of-the-art privacy-preserving clustering algorithms tend to output clusters that are good in terms of the standard metrics, inertia, silhouette score, and clustering accuracy, however, the clustering result strongly deviates from the non-private KMeans baseline. In this work, we present a privacy-preserving clustering algorithm called DPM that recursively separates a data set into clusters based on a geometrical clustering approach. In addition, DPM estimates most of the data-dependent hyper-parameters in a privacy-preserving way. We prove that DPM preserves Differential Privacy and analyse the utility guarantees of DPM. Finally, we conduct an extensive empirical evaluation for synthetic and real-life data sets. We show that DPM achieves state-of-the-art utility on the standard clustering metrics and yields a clustering result much closer to that of the popular non-private KMeans algorithm without requiring the number of classes.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 273-287
Open AccessDPM: Clustering Sensitive Data through Separation
Clustering is an important tool for data exploration where the goal is to subdivide a data set into disjoint clusters that fit well into the underlying data structure. When dealing with sensitive data, privacy-preserving algorithms aim to approximate the non-private baseline while minimising the leakage of sensitive information. State-of-the-art privacy-preserving clustering algorithms tend to output clusters that are good in terms of the standard metrics, inertia, silhouette score, and clustering accuracy, however, the clustering result strongly deviates from the non-private KMeans baseline. In this work, we present a privacy-preserving clustering algorithm called DPM that recursively separates a data set into clusters based on a geometrical clustering approach. In addition, DPM estimates most of the data-dependent hyper-parameters in a privacy-preserving way. We prove that DPM preserves Differential Privacy and analyse the utility guarantees of DPM. Finally, we conduct an extensive empirical evaluation for synthetic and real-life data sets. We show that DPM achieves state-of-the-art utility on the standard clustering metrics and yields a clustering result much closer to that of the popular non-private KMeans algorithm without requiring the number of classes.
- Open Access
- 13 June 2024
- Published by Springer Nature in KI - Künstliche Intelligenz
- Vol. 38 (3) , 225-241
Lifting in Support of Privacy-Preserving Probabilistic Inference
Privacy-preserving inference aims to avoid revealing identifying information about individuals during inference. Lifted probabilistic inference works with groups of indistinguishable individuals, which has the potential to prevent tracing back a query result to a particular individual in a group. Therefore, we investigate how lifting, by providing anonymity, can help preserve privacy in probabilistic inference. Specifically, we show correspondences between k-anonymity and lifting and present s-symmetry as an analogue as well as PAULI, a privacy-preserving inference algorithm that ensures s-symmetry during query answering.
- 13 June 2024
- Published by Springer Nature in KI - Künstliche Intelligenz
- Vol. 38 (3) , 225-241
Open AccessLifting in Support of Privacy-Preserving Probabilistic Inference
Privacy-preserving inference aims to avoid revealing identifying information about individuals during inference. Lifted probabilistic inference works with groups of indistinguishable individuals, which has the potential to prevent tracing back a query result to a particular individual in a group. Therefore, we investigate how lifting, by providing anonymity, can help preserve privacy in probabilistic inference. Specifically, we show correspondences between k-anonymity and lifting and present s-symmetry as an analogue as well as PAULI, a privacy-preserving inference algorithm that ensures s-symmetry during query answering.
- Open Access
- 9 January 2024
- Published by Springer Nature in KI - Künstliche Intelligenz
- Vol. 38 (3) , 183-188
PrivAgE: A Toolchain for Privacy-Preserving Distributed Aggregation on Edge-Devices
Valuable insights, such as frequently visited environments in the wake of the COVID-19 pandemic, can oftentimes only be gained by analyzing sensitive data spread across edge-devices like smartphones. To facilitate such an analysis, we present a toolchain called PrivAgE for a distributed, privacy-preserving aggregation of local data by taking the limited resources of edge-devices into account. The distributed aggregation is based on secure summation and simultaneously satisfies the notion of differential privacy. In this way, other parties can neither learn the sensitive data of single clients nor a single client’s influence on the final result. We perform an evaluation of the power consumption, the running time and the bandwidth overhead on real as well as simulated devices and demonstrate the flexibility of our toolchain by presenting an extension of the summation of histograms to distributed clustering.
- 9 January 2024
- Published by Springer Nature in KI - Künstliche Intelligenz
- Vol. 38 (3) , 183-188
Open AccessPrivAgE: A Toolchain for Privacy-Preserving Distributed Aggregation on Edge-Devices
Valuable insights, such as frequently visited environments in the wake of the COVID-19 pandemic, can oftentimes only be gained by analyzing sensitive data spread across edge-devices like smartphones. To facilitate such an analysis, we present a toolchain called PrivAgE for a distributed, privacy-preserving aggregation of local data by taking the limited resources of edge-devices into account. The distributed aggregation is based on secure summation and simultaneously satisfies the notion of differential privacy. In this way, other parties can neither learn the sensitive data of single clients nor a single client’s influence on the final result. We perform an evaluation of the power consumption, the running time and the bandwidth overhead on real as well as simulated devices and demonstrate the flexibility of our toolchain by presenting an extension of the summation of histograms to distributed clustering.