arXiv subjects

Thorsten Strufe

Publications and source records attributed to Thorsten Strufe.

At least 19 recordsLinked to original sources

arXiv2026

5GDescrambler: Locating, Descrambling, and Decoding 5G Scheduling Information (long version)

Tracking users in 5G NR has recently been successfully demonstrated by exploiting various side-channels. This allows for identification of individuals, classification of user activity in real time as well as tracking by fingerprinting, affecting billions of users with a 5G subscription and companies with private 5G deployments. However, previous work relies on weak operator configurations that leak networking parameters--either the radio network temporary identifier (RNTI) or scrambling factor ($N_{ID}$) during handshake--or to inefficiently brute-force Downlink Control Information (DCI). In this paper we present a novel technique exploiting algebraic structure to reverse DCI scrambling, fully integrated into an open-source end-to-end binary DCI sniffing pipeline. It provides enabling input for subsequent attacks like live tracking of users and supports automatic detection of control channel configurations used. We demonstrate the robustness and performance of our approach with measurement campaigns against deployments of srsRAN, OpenAirInterface5G, and two commercial vendors. It reaches block error rates of less than $1\%$ at SNRs below expected values for efficient communication, while performing significantly faster on a reference sample than a previously suggested passive technique brute-forcing the required parameters. In addition, it is entirely passive and does not rely on any side-channel leakage.

cs.CR↗

arXiv2026

MultiGait: A Multi-Sensor Multi-Perspective Multi-Session Biometric Inference Benchmark and its Dataset

A lack of suitable datasets has limited the research into the privacy risks of novel smart city sensors, such as thermal cameras, depth cameras, and lidar. Given the number of unsubstantiated privacy claims and their potential widespread deployment into many people's everyday life, understanding the privacy risks of these sensors -- in isolation and in like-for-like comparisons -- is crucial. With MultiGait, we collected the first multi-sensor, multi-perspective, multi-session gait-focused dataset, for the corresponding, and additional more far-reaching investigations. The dataset, validated with multiple state-of-the-art recognition systems, comprises various walking modes and annotated personal attributes for 199 individuals, to ensure the benefit for advanced studies including cross-sensor recognition and anonymization at the edge. MultiGait represents a foundation for rigorous privacy investigations, demonstrated through an extensive identity inference benchmark across eight sensors, four perspectives, and three recording sessions. Our benchmark incidentally reveals that sensors often assumed to be privacy-friendly do still entail considerable identity inference risks, while the poor cross-session generalization of existing methods underscores an important research gap.

cs.CR↗

arXiv2026

OmniSphinx: Active Mix Networks (Extended Version)

Mix networks are an important tool to implement anonymous communication, which protects not just the content but also the metadata of messages. Over time, various packet formats for mix networks have been proposed, usually with single, specific goals in mind. These formats are incompatible with each other, requiring separate software and infrastructure to be set up. In this paper, we propose a new format, OmniSphinx, which solves this issue. In OmniSphinx, senders embed code in their packets that determines how they must be processed. The resulting active mix network can emulate any other mix format within a single deployment. Our empirical evaluation shows that emulation in OmniSphinx incurs reasonable overhead compared to native execution for typical mix network use cases: For Sphinx, the most compact format, computation time increases by around 90{\mu}s, while headers increase by 33% in size.

cs.CR↗

arXiv2026

NeuroShield: A Device-Agnostic Foundation Model for EEG Authentication

A central challenge in EEG authentication is that models are typically tied to the acquisition settings in which they are trained. In particular, variations in headset hardware, channel layout, and signal duration create heterogeneous recordings that existing models are not designed to handle, causing each new headset or dataset to be treated as a separate model-development problem. This fragmentation limits multi-dataset learning, hinders knowledge transfer, and reduces model reusability. To address this limitation, we present NeuroShield, a reusable foundation model for EEG authentication that learns identity-discriminative embeddings from variable-channel and variable-length EEG recordings through a dual-stage transformer architecture. We pretrain NeuroShield on three public EEG datasets comprising 15{,}762 subjects and 28{,}116 sessions, and evaluate transfer on two unseen downstream datasets. Our evaluations show that, after fine-tuning, NeuroShield reduces equal error rate by 0.44--8.06 percentage points relative to the state of the art. NeuroShield further generalizes to segments longer than those seen during training and operates across channel layouts not encountered during pretraining. These results establish NeuroShield as a reusable and adaptable EEG identity encoder across heterogeneous recording settings. We release NeuroShield as open source to support reproducibility and community adoption.

cs.LG↗

arXiv2026

FoSAM: Forward Secret Messaging in Ad-Hoc Networks

Apps such as Firechat and Bridgefy have been used during recent protests in Hong Kong and Iran, as they allow communication over ad-hoc wireless networks even when internet access is restricted. However, these apps do not provide sufficient protection as they do not achieve forward secrecy in unreliable networks. Without forward secrecy, caught protesters' devices will disclose all previous messages to the authorities, putting them and others at great risk. In this paper, we introduce FoSAM, the first protocol to provide proven anonymous and forward secret messaging in unreliable ad-hoc networks. Communication in FoSAM requires only the receiver's public key, rather than an interactive handshake. We evaluate the performance of FoSAM using a large-scale simulation with different user movement patterns, showing that it achieves between 92% and 99% successful message delivery. We additionally implement a FoSAM prototype for Android.

cs.CR↗

arXiv2026

Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing (Extended Version)

Differential Privacy (DP) is widely adopted in data management systems to enable data sharing with formal disclosure guarantees. A central systems challenge is understanding how DP noise translates into effective protection against inference attacks, since this directly determines achievable utility. Most existing analyses focus only on membership inference -- capturing only a threat -- or rely on reconstruction robustness (ReRo). However, under realistic assumptions, we show that ReRo can yield misleading risk estimates and violate claimed bounds, limiting their usefulness for principled DP calibration and auditing. This paper introduces reconstruction advantage, a unified risk metric that consistently captures risk across membership inference, attribute inference, and data reconstruction. We derive tight bounds that relate DP noise to adversarial advantage and characterize optimal adversarial strategies for arbitrary DP mechanisms and attacker knowledge. These results enable risk-driven noise calibration and provide a foundation for systematic DP auditing. We show that reconstruction advantage improves the accuracy and scope of DP auditing and enables more effective utility-privacy trade-offs in DP-enabled data management systems.

cs.CR↗

arXiv2026

The Adverse Effects of Omitting Records in Differential Privacy: How Sampling and Suppression Degrade the Privacy--Utility Tradeoff (Long Version)

Sampling is renowned for its privacy amplification in differential privacy (DP), and is often assumed to improve the utility of a DP mechanism by allowing a noise reduction. In this paper, we further show that this last assumption is flawed: When measuring utility at equal privacy levels, sampling as preprocessing consistently yields penalties due to utility loss from omitting records over all canonical DP mechanisms -- Laplace, Gaussian, exponential, and report noisy max -- , as well as recent applications of sampling, such as clustering. Extending this analysis, we investigate suppression as a generalized method of choosing, or omitting, records. Developing a theoretical analysis of this technique, we derive privacy bounds for arbitrary suppression strategies under unbounded approximate DP. We find that our tested suppression strategy also fails to improve the privacy--utility tradeoff. Surprisingly, uniform sampling emerges as one of the best suppression methods -- despite its still degrading effect. Our results call into question common preprocessing assumptions in DP practice.

cs.CR↗

arXiv2025

FacialMotionID: Identifying Users of Mixed Reality Headsets using Abstract Facial Motion Representations

Facial motion capture in mixed reality headsets enables real-time avatar animation, allowing users to convey non-verbal cues during virtual interactions. However, as facial motion data constitutes a behavioral biometric, its use raises novel privacy concerns. With mixed reality systems becoming more immersive and widespread, understanding whether face motion data can lead to user identification or inference of sensitive attributes is increasingly important. To address this, we conducted a study with 116 participants using three types of headsets across three sessions, collecting facial, eye, and head motion data during verbal and non-verbal tasks. The data used is not raw video, but rather, abstract representations that are used to animate digital avatars. Our analysis shows that individuals can be re-identified from this data with up to 98% balanced accuracy, are even identifiable across device types, and that emotional states can be inferred with up to 86% accuracy. These results underscore the potential privacy risks inherent in face motion tracking in mixed reality environments.

cs.CR↗

arXiv2025

Balancing Privacy and Utility in Correlated Data: A Study of Bayesian Differential Privacy

Privacy risks in differentially private (DP) systems increase significantly when data is correlated, as standard DP metrics often underestimate the resulting privacy leakage, leaving sensitive information vulnerable. Given the ubiquity of dependencies in real-world databases, this oversight poses a critical challenge for privacy protections. Bayesian differential privacy (BDP) extends DP to account for these correlations, yet current BDP mechanisms indicate notable utility loss, limiting its adoption. In this work, we address whether BDP can be realistically implemented in common data structures without sacrificing utility -- a key factor for its applicability. By analyzing arbitrary and structured correlation models, including Gaussian multivariate distributions and Markov chains, we derive practical utility guarantees for BDP. Our contributions include theoretical links between DP and BDP and a novel methodology for adapting DP mechanisms to meet the BDP requirements. Through evaluations on real-world databases, we demonstrate that our novel theorems enable the design of BDP mechanisms that maintain competitive utility, paving the way for practical privacy-preserving data practices in correlated settings.

cs.CR↗

arXiv2025

Adversarial Subspace Generation for Outlier Detection in High-Dimensional Data

Outlier detection in high-dimensional tabular data is challenging since data is often distributed across multiple lower-dimensional subspaces -- a phenomenon known as the Multiple Views effect (MV). This effect led to a large body of research focused on mining such subspaces, known as subspace selection. However, as the precise nature of the MV effect was not well understood, traditional methods had to rely on heuristic-driven search schemes that struggle to accurately capture the true structure of the data. Properly identifying these subspaces is critical for unsupervised tasks such as outlier detection or clustering, where misrepresenting the underlying data structure can hinder the performance. We introduce Myopic Subspace Theory (MST), a new theoretical framework that mathematically formulates the Multiple Views effect and writes subspace selection as a stochastic optimization problem. Based on MST, we introduce V-GAN, a generative method trained to solve such an optimization problem. This approach avoids any exhaustive search over the feature space while ensuring that the intrinsic data structure is preserved. Experiments on 42 real-world datasets show that using V-GAN subspaces to build ensemble methods leads to a significant increase in one-class classification performance -- compared to existing subspace selection, feature selection, and embedding methods. Further experiments on synthetic data show that V-GAN identifies subspaces more accurately while scaling better than other relevant subspace selection methods. These results confirm the theoretical guarantees of our approach and also highlight its practical viability in high-dimensional settings.

cs.LG↗

arXiv2025

Advancing Brainwave-Based Biometrics: A Large-Scale, Multi-Session Evaluation

The field of brainwave-based biometrics has gained attention for its potential to revolutionize user authentication through hands-free interaction, resistance to shoulder surfing, continuous authentication, and revocability. However, current research often relies on single-session or limited-session datasets with fewer than 55 subjects, raising concerns about the generalizability of the findings. To address this gap, we conducted a large-scale study using a public brainwave dataset comprising 345 subjects and over 6,007 sessions (an average of 17 per subject) recorded over five years using three headsets. Our results reveal that deep learning approaches significantly outperform hand-crafted feature extraction methods. We also observe Equal Error Rates (EER) increases over time (e.g., from 6.7% after 1 day to 14.3% after a year). Therefore, it is necessary to reinforce the enrollment set after successful login attempts. Moreover, we demonstrate that fewer brainwave measurement sensors can be used, with an acceptable increase in EER, which is necessary for transitioning from medical-grade to affordable consumer-grade devices. Finally, we compared our results to prior work and existing biometric standards. While our performance is on par with or exceeds previous approaches, it still falls short of industrial benchmarks. Based on the results, we hypothesize that further improvements are possible with larger training sets. To support future research, we have open-sourced our analysis code.

eess.SP↗

arXiv2025

Pantomime: Motion Data Anonymization using Foundation Motion Models

Human motion is a behavioral biometric trait that can be used to identify individuals and infer private attributes such as medical conditions. This poses a serious threat to privacy as motion extraction from video and motion capture are increasingly used for a variety of applications, including mixed reality, robotics, medicine, and the quantified self. In order to protect the privacy of the tracked individuals, anonymization techniques that preserve the utility of the data are required. However, anonymizing motion data is a challenging task because there are many dependencies in motion sequences (such as physiological constraints) that, if ignored, make the anonymized motion sequence appear unnatural. In this paper, we propose Pantomime, a full-body anonymization technique for motion data, which uses foundation motion models to generate motion sequences that adhere to the dependencies in the data, thus keeping the utility of the anonymized data high. Our results show that Pantomime can maintain the naturalness of the motion sequences while reducing the identification accuracy to 10%.

cs.CR↗

arXiv2025

On the Reliability of Biometric Datasets: How Much Test Data Ensures Reliability?

Biometric authentication is increasingly popular for its convenience and accuracy. However, while recent advancements focus on reducing errors and expanding modalities, the reliability of reported performance metrics often remains overlooked. Understanding reliability is critical, as it communicates how accurately reported error rates represent a system's actual performance, considering the uncertainty in error-rate estimates from test data. Currently, there is no widely accepted standard for reporting these uncertainties and indeed biometric studies rarely provide reliability estimates, limiting comparability and interpretation. To address this gap, we introduce BioQuake--a measure to estimate uncertainty in biometric verification systems--and empirically validate it on four systems and three datasets. Based on BioQuake, we provide simple guidelines for estimating performance uncertainty and facilitating reliable reporting. Additionally, we apply BioQuake to analyze biometric recognition performance on 62 biometric datasets used in research across eight modalities: face, fingerprint, gait, iris, keystroke, eye movement, Electroencephalogram (EEG), and Electrocardiogram (ECG). Our analysis shows that reported state-of-the-art performance often deviates significantly from actual error rates, potentially leading to inaccurate conclusions. To support researchers and foster the development of more reliable biometric systems and datasets, we release BioQuake as an easy-to-use web tool for reliability calculations.

cs.CR↗

arXiv2024

R+R:Understanding Hyperparameter Effects in DP-SGD

Research on the effects of essential hyperparameters of DP-SGD lacks consensus, verification, and replication. Contradictory and anecdotal statements on their influence make matters worse. While DP-SGD is the standard optimization algorithm for privacy-preserving machine learning, its adoption is still commonly challenged by low performance compared to non-private learning approaches. As proper hyperparameter settings can improve the privacy-utility trade-off, understanding the influence of the hyperparameters promises to simplify their optimization towards better performance, and likely foster acceptance of private learning. To shed more light on these influences, we conduct a replication study: We synthesize extant research on hyperparameter influences of DP-SGD into conjectures, conduct a dedicated factorial study to independently identify hyperparameter effects, and assess which conjectures can be replicated across multiple datasets, model architectures, and differential privacy budgets. While we cannot (consistently) replicate conjectures about the main and interaction effects of the batch size and the number of epochs, we were able to replicate the conjectured relationship between the clipping threshold and learning rate. Furthermore, we were able to quantify the significant importance of their combination compared to the other hyperparameters.

cs.LG↗

arXiv2024

SEBA: Strong Evaluation of Biometric Anonymizations

Biometric data is pervasively captured and analyzed. Using modern machine learning approaches, identity and attribute inferences attacks have proven high accuracy. Anonymizations aim to mitigate such disclosures by modifying data in a way that prevents identification. However, the effectiveness of some anonymizations is unclear. Therefore, improvements of the corresponding evaluation methodology have been proposed recently. In this paper, we introduce SEBA, a framework for strong evaluation of biometric anonymizations. It combines and implements the state-of-the-art methodology in an easy-to-use and easy-to-expand software framework. This allows anonymization designers to easily test their techniques using a strong evaluation methodology. As part of this discourse, we introduce and discuss new metrics that allow for a more straightforward evaluation of the privacy-utility trade-off that is inherent to anonymization attempts. Finally, we report on a prototypical experiment to demonstrate SEBA's applicability.

cs.CR↗

arXiv2024

Resilience-by-Design in 6G Networks: Literature Review and Novel Enabling Concepts

The sixth generation (6G) mobile communication networks are expected to intelligently integrate into various aspects of modern digital society, including smart cities, homes, health-care, transportation, and factories. While offering a multitude of services, it is likely that societies become increasingly reliant on 6G infrastructure. Any disruption to these digital services, whether due to human or technical failures, natural disasters, or terrorism, would significantly impact citizens' daily lives. Hence, 6G networks need not only to provide high-performance services but also to be resilient in maintaining essential services in the face of potentially unknown challenges. This paper provides a general review of the state of the art on resilient systems, definitions, concepts, and approaches. Moreover, it introduces a comprehensive concept, i.e., resilience-by-design (RBD), in three different levels for designing resilient 6G communication networks, summarizing our initial studies within the German Open6GHub project. First, we outline the general RBD enabling principles and discuss their related sub-categories. Next, adopting an interdisciplinary approach, we propose to embed these principles across all 6G layers/perspectives including electronics, physical channel, network components and functions, networks, services, and cross-layer and cross-infrastructure considerations and discuss their challenges. We further elaborate the RBD principles and their realizations along with several 6G use-cases. The paper is concluded by presenting a comprehensive list of open problems for future research on 6G resilience.

cs.NI↗

arXiv2024

Beyond Gaze Points: Augmenting Eye Movement with Brainwave Data for Multimodal User Authentication in Extended Reality

Extended Reality (XR) technologies are becoming integral to daily life. However, password-based authentication in XR disrupts immersion due to poor usability, as entering credentials with XR controllers is cumbersome and error-prone. This leads users to choose weaker passwords, compromising security. To improve both usability and security, we introduce a multimodal biometric authentication system that combines eye movements and brainwave patterns using consumer-grade sensors that can be integrated into XR devices. Our prototype, developed and evaluated with 30 participants, achieves an Equal Error Rate (EER) of 0.29%, outperforming eye movement (1.82%) and brainwave (4.92%) modalities alone, as well as state-of-the-art biometric alternatives (EERs between 2.5% and 7%). Furthermore, this system enables seamless authentication through visual stimuli without complex interaction.

cs.CR↗

arXiv2024

Pirates: Anonymous Group Calls Over Fully Untrusted Infrastructure

Anonymous metadata-private voice call protocols suffer from high delays and so far cannot provide group call functionality. Anonymization inherently yields delay penalties, and scaling signalling and communication to groups of users exacerbates this situation. Our protocol Pirates employs PIR, improves parallelization and signalling, and is the first group voice call protocol that guarantees the strong anonymity notion of communication unobservability. Implementing and measuring a prototype, we show that Pirates with a single server can support group calls with three group members from an 11 concurrent users with mouth-to-ear latency below 365ms, meeting minimum ITU requirements as the first anonymous voice call system. Increasing the number of servers enables bigger group sizes and more participants.

cs.CR↗