Alexandra Dmitrienko

Alexandra Dmitrienko

Auto-generated profile, based on publicly available information

Alexandra Dmitrienko

University of Duisburg-Essen

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 November 2023
Verified
Conference Paper
Open access
TKTorsten Krauß
Torsten Krauß
ADAlexandra Dmitrienko
Alexandra Dmitrienko
Federated Learning (FL) enhances decentralized machine learning by safeguarding data privacy, reducing communication costs, and improving model performance with diverse data sources. However, FL faces vulnerabilities such as untargeted poisoning attacks and targeted backdoor attacks, posing challenges to model integrity and security. Preventing backdoors proves especially challenging due to their stealthy nature. Existing mitigation techniques have shown efficacy but often overlook realistic adversaries and diverse data distributions. This work introduces the concept of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. Extensive empirical testing reveals existing defenses' vulnerability in this adversary model. We present Metric-Cascades (MESAS), a novel defense method tailored to more realistic scenarios and adversary models. MESAS employs multiple detection metrics simultaneously to combat poisoned model updates, posing a complex multi-objective problem for adaptive attackers. In a comprehensive evaluation across nine backdoors and three datasets, MESAS outperforms existing defenses in distinguishing backdoors from data distribution-related distortions within and across clients. MESAS offers robust defense against strong adaptive adversaries in real-world data settings, with a modest average overhead of just 24.37 seconds.

12 September 2020
Verified
Book Chapter
Closed access
PDF file
JNJens Neureither
Jens Neureither
ADAlexandra Dmitrienko
Alexandra Dmitrienko
DKDavid Koisser
David Koisser
FBFerdinand Brasser
Ferdinand Brasser
ASAhmad-Reza Sadeghi
Ahmad-Reza Sadeghi

7 November 2022 in ACM Transactions on Privacy and Security
Verified
Journal Article
Open access
CHChristoph Hagen
Christoph Hagen
CWChristian Weinert
Christian Weinert
CSChristoph Sendner
Christoph Sendner
ADAlexandra Dmitrienko
Alexandra Dmitrienko
TSThomas Schneider
Thomas Schneider
Contact discovery allows users of mobile messengers to conveniently connect with people in their address book. In this work, we demonstrate that severe privacy issues exist in currently deployed contact discovery methods and propose suitable mitigations. Our study of three popular messengers (WhatsApp, Signal, and Telegram) shows that large-scale crawling attacks are (still) possible. Using an accurate database of mobile phone number prefixes and very few resources, we queried 10 % of US mobile phone numbers for WhatsApp and 100 % for Signal. For Telegram, we find that its API exposes a wide range of sensitive information, even about numbers not registered with the service. We present interesting (cross-messenger) usage statistics, which also reveal that very few users change the default privacy settings. Furthermore, we demonstrate that currently deployed hashing-based contact discovery protocols are severely broken by comparing three methods for efficient hash reversal. Most notably, we show that with the password cracking tool “JTR,” we can iterate through the entire worldwide mobile phone number space in < 150 s on a consumer-grade GPU. We also propose a significantly improved rainbow table construction for non-uniformly distributed input domains that is of independent interest. Regarding mitigations, we most notably propose two novel rate-limiting schemes: our incremental contact discovery for services without server-side contact storage strictly improves over Signal’s current approach while being compatible with private set intersection, whereas our differential scheme allows even stricter rate limits at the overhead for service providers to store a small constant-size state that does not reveal any contact information.

27 October 2022 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
TNThien Duc Nguyen
Thien Duc Nguyen
MMMarkus Miettinen
Markus Miettinen
ADAlexandra Dmitrienko
Alexandra Dmitrienko
ASAhmad-Reza Sadeghi
Ahmad-Reza Sadeghi
IVIvan Visconti
Ivan Visconti
The COVID-19 pandemic has caused many countries to deploy novel digital contact tracing (DCT) systems to boost the efficiency of manual tracing of infection chains. In this paper, we systematically analyze DCT solutions and categorize them based on their design approaches and architectures. We analyze them with regard to effectiveness, security, privacy and ethical aspects and compare prominent solutions based on these requirements. In particular, we discuss shortcomings of the Google and Apple Exposure Notification API (GAEN) that is currently widely adopted all over the world. We find that the security and privacy of GAEN has considerable deficiencies as it can be compromised by severe large-scale attacks. We also discuss other proposed approaches for contact tracing, including our proposal TraceCORONA , that are based on Diffie-Hellman (DH) key exchange and aim at tackling shortcomings of existing solutions. Our extensive analysis shows that TraceCORONA fulfills the above security requirements better than deployed state-of-the-art approaches. We have implemented TraceCORONA and its beta test version has been used by more than 2000 users without any major functional problems https://tracecorona.net/download-tracecorona/ , demonstrating that there are no technical reasons requiring to make compromises with regard to the requirements of DCT approaches.

1 July 2024
Verified
Conference Paper
Open access
TKTorsten Krauß
Torsten Krauß
JSJasper Stang
Jasper Stang
ADAlexandra Dmitrienko
Alexandra Dmitrienko
While Machine Learning (ML) is one of the most promising technologies in our era, it is prone to a variety of attacks. One of them is covert channels, that enable two parties to stealthily transmit information through carriers intended for different purposes. Existing works only explore covert channels for federated ML. Thereby, communication is established among multiple entities that collaborate to train a model, while relying on access to model internals. This paper presents covert channels within ML models trained and publicly deployed in cloud-based (black-box) environments. The approach relies on targeted poisoning, or backdoor, attacks to encode messages into the model. It incorporates multiple well-chosen backdoors only through dataset poisoning and without requiring access to model internals or the training process. After model deployment, messages can be extracted via inference. We propose three covert channel versions with varying levels of message robustness and capacity while emphasizing minimal extraction effort, minimal pre-shared knowledge, or maximum message stealthiness. We investigate influencing factors affecting embedded backdoors and propose novel techniques to incorporate numerous backdoors simultaneously for message encoding. Experiments across various datasets and model architectures demonstrate message transmission of 20 to 66 bits with minimal error rates.

11 January 2024
Verified
Book Chapter
Closed access
PDF file
TKTorsten Krauß
Torsten Krauß
RGRaphael Götz
Raphael Götz
ADAlexandra Dmitrienko
Alexandra Dmitrienko