arXiv subjects

Helen Möllering

Publications and source records attributed to Helen Möllering.

5 recordsLinked to original sources

arXiv2025

Privacy-Preserving Epidemiological Modeling on Mobile Graphs

The latest pandemic COVID-19 brought governments worldwide to use various containment measures to control its spread, such as contact tracing, social distance regulations, and curfews. Epidemiological simulations are commonly used to assess the impact of those policies before they are implemented. Unfortunately, the scarcity of relevant empirical data, specifically detailed social contact graphs, hampered their predictive accuracy. As this data is inherently privacy-critical, a method is urgently needed to perform powerful epidemiological simulations on real-world contact graphs without disclosing any sensitive~information. In this work, we present RIPPLE, a privacy-preserving epidemiological modeling framework enabling standard models for infectious disease on a population's real contact graph while keeping all contact information locally on the participants' devices. As a building block of independent interest, we present PIR-SUM, a novel extension to private information retrieval for secure download of element sums from a database. Our protocols are supported by a proof-of-concept implementation, demonstrating a 2-week simulation over half a million participants completed in 7 minutes, with each participant communicating less than 50 KB.

cs.CR↗

arXiv2024

ScionFL: Efficient and Robust Secure Quantized Aggregation

Secure aggregation is commonly used in federated learning (FL) to alleviate privacy concerns related to the central aggregator seeing all parameter updates in the clear. Unfortunately, most existing secure aggregation schemes ignore two critical orthogonal research directions that aim to (i) significantly reduce client-server communication and (ii) mitigate the impact of malicious clients. However, both of these additional properties are essential to facilitate cross-device FL with thousands or even millions of (mobile) participants. In this paper, we unite both research directions by introducing ScionFL, the first secure aggregation framework for FL that operates efficiently on quantized inputs and simultaneously provides robustness against malicious clients. Our framework leverages (novel) multi-party computation (MPC) techniques and supports multiple linear (1-bit) quantization schemes, including ones that utilize the randomized Hadamard transform and Kashin's representation. Our theoretical results are supported by extensive evaluations. We show that with no overhead for clients and moderate overhead for the server compared to transferring and processing quantized updates in plaintext, we obtain comparable accuracy for standard FL benchmarks. Moreover, we demonstrate the robustness of our framework against state-of-the-art poisoning attacks.

cs.CR↗

arXiv2023

FLAME: Taming Backdoors in Federated Learning (Extended Version 1)

Federated Learning (FL) is a collaborative machine learning approach allowing participants to jointly train a model without having to share their private, potentially sensitive local datasets with others. Despite its benefits, FL is vulnerable to backdoor attacks, in which an adversary injects manipulated model updates into the model aggregation process so that the resulting model will provide targeted false predictions for specific adversary-chosen inputs. Proposed defenses against backdoor attacks based on detecting and filtering out malicious model updates consider only very specific and limited attacker models, whereas defenses based on differential privacy-inspired noise injection significantly deteriorate the benign performance of the aggregated model. To address these deficiencies, we introduce FLAME, a defense framework that estimates the sufficient amount of noise to be injected to ensure the elimination of backdoors while maintaining the model performance. To minimize the required amount of noise, FLAME uses a model clustering and weight clipping approach. Our evaluation of FLAME on several datasets stemming from application areas including image classification, word prediction, and IoT intrusion detection demonstrates that FLAME removes backdoors effectively with a negligible impact on the benign performance of the models. Furthermore, following the considerable attention that our research has received after its presentation at USENIX SEC 2022, FLAME has become the subject of numerous investigations proposing diverse attack methodologies in an attempt to circumvent it. As a response to these endeavors, we provide a comprehensive analysis of these attempts. Our findings show that these papers (e.g., 3DFed [36]) have not fully comprehended nor correctly employed the fundamental principles underlying FLAME, i.e., our defense mechanism effectively repels these attempted attacks.

cs.CR↗

arXiv2022

SPIKE: Secure and Private Investigation of the Kidney Exchange problem

Background: The kidney exchange problem (KEP) addresses the matching of patients in need for a replacement organ with compatible living donors. Ideally many medical institutions should participate in a matching program to increase the chance for successful matches. However, to fulfill legal requirements current systems use complicated policy-based data protection mechanisms that effectively exclude smaller medical facilities to participate. Employing secure multi-party computation (MPC) techniques provides a technical way to satisfy data protection requirements for highly sensitive personal health information while simultaneously reducing the regulatory burdens. Results: We have designed, implemented, and benchmarked SPIKE, a secure MPC-based privacy-preserving KEP which computes a solution by finding matching donor-recipient pairs in a graph structure. SPIKE matches 40 pairs in cycles of length 2 in less than 4 minutes and outperforms the previous state-of-the-art protocol by a factor of 400x in runtime while providing medically more robust solutions. Conclusions: We show how to solve the KEP in a robust and privacy-preserving manner achieving practical performance. The usage of MPC techniques fulfills many data protection requirements on a technical level, allowing smaller health care providers to directly participate in a kidney exchange with reduced legal processes.

cs.CR↗

arXiv2021

BaFFLe: Backdoor detection via Feedback-based Federated Learning

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing defensive techniques. In this paper, we propose Backdoor detection via Feedback-based Federated Learning (BAFFLE), a novel defense to secure FL against backdoor attacks. The core idea behind BAFFLE is to leverage data of multiple clients not only for training but also for uncovering model poisoning. We exploit the availability of diverse datasets at the various clients by incorporating a feedback loop into the FL process, to integrate the views of those clients when deciding whether a given model update is genuine or not. We show that this powerful construct can achieve very high detection rates against state-of-the-art backdoor attacks, even when relying on straightforward methods to validate the model. Through empirical evaluation using the CIFAR-10 and FEMNIST datasets, we show that by combining the feedback loop with a method that suspects poisoning attempts by assessing the per-class classification performance of the updated model, BAFFLE reliably detects state-of-the-art backdoor attacks with a detection accuracy of 100% and a false-positive rate below 5%. Moreover, we show that our solution can detect adaptive attacks aimed at bypassing the defense.

cs.CR↗