arXiv subjects

Franziska Boenisch

Publications and source records attributed to Franziska Boenisch.

60 records · Page 4Linked to original sources

arXiv2022

Bounding Membership Inference

Differential Privacy (DP) is the de facto standard for reasoning about the privacy guarantees of a training algorithm. Despite the empirical observation that DP reduces the vulnerability of models to existing membership inference (MI) attacks, a theoretical underpinning as to why this is the case is largely missing in the literature. In practice, this means that models need to be trained with DP guarantees that greatly decrease their accuracy. In this paper, we provide a tighter bound on the positive accuracy (i.e., attack precision) of any MI adversary when a training algorithm provides $(\varepsilon, δ)$-DP. Our bound informs the design of a novel privacy amplification scheme: an effective training set is sub-sampled from a larger set prior to the beginning of training. We find this greatly reduces the bound on MI positive accuracy. As a result, our scheme allows the use of looser DP guarantees to limit the success of any MI adversary; this ensures that the model's accuracy is less impacted by the privacy guarantee. While this clearly benefits entities working with far more data than they need to train on, it can also improve the accuracy-privacy trade-off on benchmarks studied in the academic literature. Consequently, we also find that subsampling decreases the effectiveness of a state-of-the-art MI attack (LiRA) much more effectively than training with stronger DP guarantees on MNIST and CIFAR10. We conclude by discussing implications of our MI bound on the field of machine unlearning.

cs.LG↗

arXiv2022

A Unified Framework for Quantifying Privacy Risk in Synthetic Data

Synthetic data is often presented as a method for sharing sensitive information in a privacy-preserving manner by reproducing the global statistical properties of the original data without disclosing sensitive information about any individual. In practice, as with other anonymization methods, privacy risks cannot be entirely eliminated. The residual privacy risks need instead to be ex-post assessed. We present Anonymeter, a statistical framework to jointly quantify different types of privacy risks in synthetic tabular datasets. We equip this framework with attack-based evaluations for the singling out, linkability, and inference risks, the three key indicators of factual anonymization according to the European General Data Protection Regulation (GDPR). To the best of our knowledge, we are the first to introduce a coherent and legally aligned evaluation of these three privacy risks for synthetic data, and to design privacy attacks which model directly the singling out and linkability risks. We demonstrate the effectiveness of our methods by conducting an extensive set of experiments that measure the privacy risks of data with deliberately inserted privacy leakages, and of synthetic data generated with and without differential privacy. Our results highlight that the three privacy risks reported by our framework scale linearly with the amount of privacy leakage in the data. Furthermore, we observe that synthetic data exhibits the lowest vulnerability against linkability, indicating one-to-one relationships between real and synthetic data records are not preserved. Finally, we demonstrate quantitatively that Anonymeter outperforms existing synthetic data privacy evaluation frameworks both in terms of detecting privacy leaks, as well as computation speed. To contribute to a privacy-conscious usage of synthetic data, we open source Anonymeter at https://github.com/statice/anonymeter.

cs.CR↗

arXiv2022

Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at the cost of the resulting ML models' utility. One reason for this is that DP uses one uniform privacy budget epsilon for all training data points, which has to align with the strictest privacy requirement encountered among all data holders. In practice, different data holders have different privacy requirements and data points of data holders with lower requirements can contribute more information to the training process of the ML models. To account for this need, we propose two novel methods based on the Private Aggregation of Teacher Ensembles (PATE) framework to support the training of ML models with individualized privacy guarantees. We formally describe the methods, provide a theoretical analysis of their privacy bounds, and experimentally evaluate their effect on the final model's utility using the MNIST, SVHN, and Adult income datasets. Our empirical results show that the individualized privacy methods yield ML models of higher accuracy than the non-individualized baseline. Thereby, we improve the privacy-utility trade-off in scenarios in which different data holders consent to contribute their sensitive data at different individual privacy levels.

cs.LG↗

arXiv2021

A Systematic Review on Model Watermarking for Neural Networks

Machine learning (ML) models are applied in an increasing variety of domains. The availability of large amounts of data and computational resources encourages the development of ever more complex and valuable models. These models are considered intellectual property of the legitimate parties who have trained them, which makes their protection against stealing, illegitimate redistribution, and unauthorized application an urgent need. Digital watermarking presents a strong mechanism for marking model ownership and, thereby, offers protection against those threats. This work presents a taxonomy identifying and analyzing different classes of watermarking schemes for ML models. It introduces a unified threat model to allow structured reasoning on and comparison of the effectiveness of watermarking methods in different scenarios. Furthermore, it systematizes desired security requirements and attacks against ML model watermarking. Based on that framework, representative literature from the field is surveyed to illustrate the taxonomy. Finally, shortcomings and general limitations of existing approaches are discussed, and an outlook on future research directions is given.

cs.CR↗

arXiv2021

Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of NNs. This paper experimentally evaluates the impact of training with Differential Privacy (DP), a standard method for privacy preservation, on model vulnerability against a broad range of adversarial attacks. The results suggest that private models are less robust than their non-private counterparts, and that adversarial examples transfer better among DP models than between non-private and private ones. Furthermore, detailed analyses of DP and non-DP models suggest significant differences between their gradients. Additionally, this work is the first to observe that an unfavorable choice of parameters in DP training can lead to gradient masking, and, thereby, results in a wrong sense of security.

cs.CR↗

arXiv2018

Tracking all members of a honey bee colony over their lifetime

Computational approaches to the analysis of collective behavior in social insects increasingly rely on motion paths as an intermediate data layer from which one can infer individual behaviors or social interactions. Honey bees are a popular model for learning and memory. Previous experience has been shown to affect and modulate future social interactions. So far, no lifetime history observations have been reported for all bees of a colony. In a previous work we introduced a tracking system customized to track up to $4000$ bees over several weeks. In this contribution we present an in-depth description of the underlying multi-step algorithm which both produces the motion paths, and also improves the marker decoding accuracy significantly. We automatically tracked ${\sim}2000$ marked honey bees over 10 weeks with inexpensive recording hardware using markers without any error correction bits. We found that the proposed two-step tracking reduced incorrect ID decodings from initially ${\sim}13\%$ to around $2\%$ post-tracking. Alongside this paper, we publish the first trajectory dataset for all bees in a colony, extracted from ${\sim} 4$ million images. We invite researchers to join the collective scientific effort to investigate this intriguing animal system. All components of our system are open-source.

cs.CV↗