I am a Principal Research Scientist co-leading the AI for Cyberdefence (AICD) Research Center at the Alan Turing Institute, London, UK.
My research interests lie in the intersection of Systems Security and Machine Learning (i.e., ML4Sec). This includes autonomous network defence, large traffic analysis models, and active & adaptive adversaries. I am passionate about deep reinforcement learning, transformers and their applications in security problems. Please check my recent publications (see Publications and Scholar) for my published papers and preprints in this area. I hold a PhD in Computer Security.
My research has been published in top-tier academic and industrial venues such as the ACM Conference on Computer and Communications Security (CCS), NeurIPS, the Privacy Enhancing Technologies Symposium (PETs), the Network & Distributed System Security Symposium (NDSS) etc. Moreover, I frequent the top venues for security practitionaires (BlackHat US and BlackHat EU, Defcon, the Chaos Communication Congress) and present my team's research results. I have been kindly supported by Oasis Labs, Binance Labs, the Allan & Nesta Ferguson Charitable Trust and the UCL Public Engagement Unit. I have also been honored to be in the 10-of-200 young researchers' list by the Heidelberg Laureate Forum, a recipient of the Werner Romberg Grant, as well as a finalist at the CSAW Europe 2018 Applied Research Competition.
Besides my main research direction, I have worked on a variety of other projects. Snappy is a fast-payment solution for slow permissionless blockchains. Myst is a high-assurance cryptographic hardware prototype which was the first trojan-resilient deployment that achieved performance similar to that of conventional hardware security modules used in production (CSAW 2018 Competition Finalist). Our study on ultrasound tracking received wide-spread attention and is considered the seminal work in this area. With Petr Svenda, we released the first open-source cryptographic library for JavaCards. Finally, I have published a stream of papers studying market fairness & manipulation as security problems. I hold a PhD in the Information Security Group at University College London.
Encrypted Traffic Classification using High-dimensional Embeddings
This project studies the resilience of encrypted-communications schemes against adversaries that intent to breach the privacy of individual users. To evaluate widely-used schemes, we employ deep neural network models so as to map encrypted traffic traces into high-dimensional representations (see figure on the left). This enables us to generate a database of labeled traces that can then be used to classify unlabeled samples based on their proximity. Our results show that communication patterns suffice to reconstruct user activity with high accuracy and thus widely-deployed encrypted-communications systems offer weaker privacy guarantees than previously thought. This paper and the corresponding defence tools are currently under submission.[Paper]
Information Leakage Classification with Deep Neural Networks
Near-field microprobes have the capability to isolate small regions of a chip surface and enable precise measurements with high spatial resolution. Being able to distinguish the activity of small regions has given rise to attacks that exploit the spatial dependencies of cryptographic algorithms in order to recover the secret key. This project introduces a set of techniques that allow security researchers to evaluate the leakage properties of any chip. We show that deep neural network models outperform previously proposed methods (e.g., difference of means, multivariate templates), especially in the context of single-shot classification and small memory regions. We validate the practicality of our proposed models by classifying the leakages from the SRAM of a modern ARM Cortex-M4 chip. Our results show that we were able to always distinguish the activity between 2 SRAM regions of 128 bytes each, while for 256 SRAM single-byte regions we achieve 32% accuracy.[Paper]
MultiBallot: A Scheme for Privacy-preserving, Verifiable Statistics
Processing sensitive data for scientific purposes has the potential to bring substantial benefits both to individuals and society, however, it also requires strong guarantees that the data will not be used inappropriately. This project attempts to address some of the open challenges in the area: 1) effective ways to hold data processors accountable, 2) preserving the privacy of individuals and 3) protect the integrity of their data. For this purpose, we introduce MultiBallot, a privacy-preserving scheme that allows organizations to publish statistics derived from sensitive user data without breaching the privacy of the individual data subjects. Our scheme is based on ThreeBallot, a paper-voting design that allows voters to verify both the result of the elections (univariate operation) and that their individual vote was counted towards it. Our work extends this scheme and enables users to compute multivariate statistics on the published data. Moreover, MultiBallot can provide strong data integrity guarantees and public verifiability, when combined with a high-integrity data structure (e.g., a blockchain). These additional features make MultiBallot applicable in a wide range of data-processing scenarios such as healthcare statistics and communication records.[Paper]
Leakage-Resilient Protocols for Cryptographic Operations
Cryptographic devices used in critical applications operate under the assumption that hardware components remain always compliant with their specifications. Consequently, components that contain intentional or unintentional errors (e.g., bugs, hardware trojans, backdoors) cannot reliably maintain any of their security properties. In this work, we relax this strict correctness requirement and demonstrate how trusted, high-assurance hardware can be built from untrusted and potentially malicious components. We employ more than a hundred COTS secure cryptocoprocessors, verified to FIPS140-2 Level 4 tamper-resistance standards, and use them to realize high-confidentiality random number generation, key derivation, public key decryption and signing. Our experiments show a reasonable computational overhead (less than 1% for both Decryption and Signing) and an exponential increase in backdoor-tolerance as more ICs are added.SoK: Automated Vulnerability Detection
Shereen E., Ristea D., Vyas S., McFadden S., Dwyer M., Hicks C., Mavroudis V, Under submission 2024
Benchmarking OpenAI o1 in Cyber Security
Ristea D., Mavroudis V., Hicks C., 2024
CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents [Repository]
Emerson H., Bates L., Hicks C., Mavroudis V., 2024
Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously [PDF]
Stephen P., Hicks C., Mavroudis V., Herbster, M., NeurIPS, 2024 [Spotlight]
Entity-based Reinforcement Learning for Autonomous Cyber Defence
Thompson I., Caron A., Hicks C., Mavroudis V., Workshop on Autonomous Cybersecurity (AutonomousCyber), 2024
Environment Complexity and Nash Equilibria in a Sequential Social Dilemma
Yasir M., Howes A., Mavroudis V., Hicks C., 17th European Workshop on Reinforcement Learning (EWRL), 2024
Autonomous cyber defence: Beyond games? [PDF]
Hicks C., Mavroudis V., Turing Report, 2024
International Scientific Report on the Safety of Advanced AI [PDF]
Bengio Y., Privitera D., Besiroglu T., Bommasani R., Casper S., Choi Y., Goldfarb D., Heidari H., Khalatbari L., Mavroudis V., Longpre S., Interim Report, 2024
A View on Out-of-Distribution Identification from a Statistical Testing Theory Perspective [PDF]
Caron A., Hicks C., Mavroudis V., ArXiv, 2024
Fusion Encoder Networks [PDF]
Stephen P., Hicks C., Mavroudis V., ArXiv, 2024
Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space [PDF]
Vyas S., Hicks C., Mavroudis V., Deep Learning Security and Privacy Workshop (DLSP), 2024
Deep Reinforcement Learning for Denial-of-Service Query Discovery in GraphQL [PDF]
McFadden S., Maugeri M., Hicks C., Mavroudis V., Pierazzi F., Deep Learning Security and Privacy Workshop (DLSP), 2024
Nearest Neighbour with Bandit Feedback [PDF]
Pasteris S., Hicks C., Mavroudis V., Annual Conference on Neural Information Processing Systems (NeurIPS), 2023
Adaptive Webpage Fingerprinting from TLS Traces
Mavroudis V., Hayes J., 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2023
Reward Shaping for Happier Autonomous Cyber Security Agents
Bates E., Mavroudis V., Hicks C., 16th ACM Workshop on Artificial Intelligence and Security (AISec), 2023
Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning
Hicks C., Mavroudis V., Foley M., Davies T., Highnam K., Watson T., 16th ACM Workshop on Artificial Intelligence and Security (AISec), 2023
Autonomous network defence using reinforcement learning
Foley M., Hicks C., Highnam K., Mavroudis V., Asia Conference on Computer and Communications Security (AsiaCCS), 2022
Inroads into Autonomous Network Defence using Explained Reinforcement Learning [PDF]
Foley M., Wang M., Hicks C., Mavroudis V., Conference on Applied Machine Learning in Information Security (CAMLIS), 2022
SIMple ID: QR Codes for Authentication Using Basic Mobile Phones in Developing Countries [PDF]
Hicks C., Mavroudis V., Crowcroft J., The 18th International Workshop on Security and Trust Management (STM), 2022
An Interface Between Legacy and Modern Mobile Devices for Digital Identity [PDF]
Mavroudis V., Hicks C., Crowcroft J., International Workshop on Emerging Technologies for Authorization and Authentication (ETAA), 2021
JCMathLib: Wrapper Cryptographic Library for Transparent and Certifiable JavaCard Applets [PDF]
Mavroudis V., Svenda P., IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), March 2020
Snappy: Fast Blockchain Payments [PDF]
Mavroudis V., , Wuest K., Dhar A., Kostiainen K., Capkun S., Network & Distributed System Security Symposium (NDSS), Feb 2020
Location, location, location: Revisiting modeling and exploitation for location-based side channel leakages. [PDF]
Andrikos C., Batina L., Chmielewski L., Lerman L., Mavroudis V., Papagiannopoulos K., Perin G., Rassias G., Sonnino A.,
25th Annual International Conference on the Theory and Application of Cryptology and Information Security (AsiaCrypt) 2019
Libra: Fair Order-Matching for Electronic Financial Exchanges. [PDF]
Mavroudis V., Melton H., Advances in Financial Technologies AFT 2019, October 2019
Bounded Temporal Fairness for FIFO Financial Markets. [PDF]
Mavroudis V., 26th International Workshop on Security Protocols SPW, April 2019
Market Manipulation as a Security Problem: Attacks and Defenses [PDF]
Mavroudis V., 12th European Workshop on Systems Security EuroSec, March 2019
Towards Low-level Cryptographic Primitives for JavaCards.
Mavroudis V., Svenda P., Oct 2018
VAMS: Verifiable Auditing of Access to Confidential Data.
Hicks A., Mavroudis V., Al-Bassam M., Meiklejohn S., Murdoch S., May 2018
Eavesdropping Whilst Youre Shopping: Balancing Personalisation and Privacy in Connected Retail Spaces [PDF]
Mavroudis V., Veale M. (Equal Contribution), PETRAS/IoTUK/IET Living in the IoT Conference, 2018.
A Touch of Evil: High-Assurance Cryptographic Hardware from Untrusted Components [PDF, ArXiv]
Mavroudis V., Cerulli A., Svenda P., Cvrcek D., Klinec D., Danezis G., 24th ACM Conference on Computer and Communications Security CCS, 2017.
CSAW 2018 Applied Research Competition Finalist.
On the Privacy and Security of the Ultrasound Tracking Ecosystem [PDF]
Mavroudis V., Hao S., Fratantonio Y., Maggi F., Kruegel C., Vigna G., Proceedings of the Privacy Enhancing Technologies Symposium PETs, 2017
Visual Analytics for Enhancing Supervised Attack Attribution in Mobile Networks [PDF]
Papadopoulos S., Mavroudis V., Drosou A., Tzovaras D., 29th International Symposium on Computer and Information Sciences, 2014
The Ultrasound Tracking Ecosystem.
Vasilios Mavroudis, Shuang Hao, Yanick Fratantonio, Federico Maggi, Giovanni Vigna, and Christopher Kruegel. November 2016
Correlation Analysis and Abnormal Event Detection Module.
EU FP7 Project: Enhanced Network Security for Seamless Service Provisioning in the Smart Mobile Ecosystem
Anomaly detection based on real-time exploitation of billing systems.
EU FP7 Project: Enhanced Network Security for Seamless Service Provisioning in the Smart Mobile Ecosystem
Anomaly detection within femtocell architectures.
EU FP7 Project: Enhanced Network Security for Seamless Service Provisioning in the Smart Mobile Ecosystem
Network information sources.
EU FP7 Project: Enhanced Network Security for Seamless Service Provisioning in the Smart Mobile Ecosystem
Crux: Privacy-preserving Statistics for Tor [PDF], Information Security Group, University College London, UK, 2015.
Supervisor: George Danezis
Cassiopeia: Real-time mobile security monitoring system, Dept. of Applied Informatics, University of Macedonia, Greece, 2012.
Supervisor: Ioannis Mavridis