Publications (66)
PHom-GeM: Persistent Homology for Generative Models
Jeremy Charlier, Radu State, Jean Hilger
Generative neural network models, including Generative Adversarial Network (GAN) and Auto-Encoders (AE), are among the most popular neural network models to generate adversarial da…
Deep dive into Interledger: Understanding the Interledger ecosystem
Lucian Trestioreanu, Cyril Cassagnes, Radu State
At the technical level, the goal of Interledger is to provide an architecture and a minimal set of protocols to enable interoperability between any value transfer systems. The Inte…
Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory
Tatiana Petrova, Evgeny Polyachenko, Radu State
We study the thermodynamic memory capacity of modern Hopfield networks (Dense Associative Memory models) with continuous states under geometric constraints, extending classical ana…
Topology Analysis of the XRP Ledger
Vytautas Tumas, Sean Rivera, Damien Magoni +1
XRP Ledger is one of the oldest, well-established blockchains. Despite the popularity of the XRP Ledger, little is known about its underlying peer-to-peer network. The structural p…
Frontrunner Jones and the Raiders of the Dark Forest: An Empirical Study of Frontrunning on the Ethereum Blockchain
Christof Ferreira Torres, Ramiro Camino, Radu State
Ethereum prospered the inception of a plethora of smart contract applications, ranging from gambling games to decentralized finance. However, Ethereum is also considered a highly a…
QeHDC: Hyperdimensional Computing based on Quantum-enhanced binding and SuperClass Construction
Yangjie Xu, Hui Huang, Li Ning +1
Hyperdimensional Computing (HDC) is a robust computational framework inspired by human cognition characterized by simple and efficient operations within high-dimensional vector spa…
HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
Loris Bergeron, Ioana Buhnila, Jérôme François +1
Large Language Models (LLMs) excel in many NLP tasks but remain prone to hallucinations, limiting trust in real-world applications. We present HalluGuard, a 4B-parameter Small Reas…
Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videos
Lujun Li, Lama Sleem, Yiqun Wang +3
Recent research on time-series foundation models (TSFMs) has underscored the scarcity of real-world data, often supplemented with synthetic sources in existing datasets, whose gene…
SoK: Cryptographic Key Recovery for Cryptoasset Custody and Financial Technologies
Francisco Javier Becerra Sanchez, Antonio Ken Iannillo, Radu State
Cryptoasset systems often bind cryptographic key control to financial control: losing a wallet seed, custody share, hardware device, or smart-account credential can remove spend au…
Large-Scale Detection of Non-Technical Losses in Imbalanced Data Sets
Patrick O. Glauner, Andre Boechat, Lautaro Dolberg +4
Non-technical losses (NTL) such as electricity theft cause significant harm to our economies, as in some countries they may range up to 40% of the total electricity distributed. De…
Generating Multi-Categorical Samples with Generative Adversarial Networks
Ramiro Camino, Christian Hammerschmidt, Radu State
We propose a method to train generative adversarial networks on mutivariate feature vectors representing multiple categorical values. In contrast to the continuous domain, where GA…
The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models
Lujun Li, Lama Sleem, Niccolo Gentile +4
Recent vision-language models (VLMs) excel at multimodal understanding and reasoning, yet their fine-grained visual perception remains underexplored. A natural extension of ``How m…
The Necessity of Setting Temperature in LLM-as-a-Judge
Lujun Li, Lama Sleem, Yangjie Xu +4
Using large language models (LLMs) as judges for evaluating model outputs has emerged as an important paradigm for automated evaluation. However, the choice of decoding temperature…
Feed-Forward Steering in Transformer Residual Dynamics
Timur Mudarisov, Mikhail Burtsev, Radu State
Attention-only dynamical theories model Transformer residual directions as particles aggregating on a sphere. We extend this framework by incorporating the feed-forward network (FF…
Blockly2Hooks: Smart Contracts for Everyone with the XRP Ledger and Google Blockly
Lucian Trestioreanu, Wazen Shbair, Flaviene Scheidt de Cristo +1
Recent technologies such as inter-ledger payments, non-fungible tokens, and smart contracts are all fruited from the ongoing development of Distributed Ledger Technologies. The for…
The Top 10 Topics in Machine Learning Revisited: A Quantitative Meta-Study
Patrick Glauner, Manxing Du, Victor Paraschiv +5
Which topics of machine learning are most commonly addressed in research? This question was initially answered in 2007 by doing a qualitative survey among distinguished researchers…
Visualization of AE's Training on Credit Card Transactions with Persistent Homology
Jeremy Charlier, Francois Petit, Gaston Ormazabal +2
Auto-encoders are among the most popular neural network architecture for dimension reduction. They are composed of two parts: the encoder which maps the model distribution to a lat…
The Eye of Horus: Spotting and Analyzing Attacks on Ethereum Smart Contracts
Christof Ferreira Torres, Antonio Ken Iannillo, Arthur Gervais +1
In recent years, Ethereum gained tremendously in popularity, growing from a daily transaction average of 10K in January 2016 to an average of 500K in January 2020. Similarly, smart…
NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks
Lama Sleem, Jerome Francois, Lujun Li +3
Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelin…
Predicting Sparse Clients' Actions with CPOPT-Net in the Banking Environment
Jeremy Charlier, Radu State, Jean Hilger
The digital revolution of the banking system with evolving European regulations have pushed the major banking actors to innovate by a newly use of their clients' digital informatio…
Geometry-Guided Layerwise FFN Width Allocation in Transformers
Timur Mudarisov, Mikhail Burtsev, Radu State
Feed-forward networks (FFNs) account for a large fraction of Transformer parameters, yet their hidden width is usually constant across depth. We ask whether this capacity can inste…
To Squelch or not to Squelch: Enabling Improved Message Dissemination on the XRP Ledger
Lucian Trestioreanu, Flaviene Scheidt, Wazen Shbair +3
With the large increase in the adoption of blockchain technologies, their underlying peer-to-peer networks must also scale with the demand. In this context, previous works highligh…
Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets
Patrick Glauner, Jorge Meira, Lautaro Dolberg +4
Electricity theft is a major problem around the world in both developed and developing countries and may range up to 40% of the total electricity distributed. More generally, elect…
Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications
Lujun Li, Yiqun Wang, Radu State
Cloud cover in multispectral imagery (MSI) poses significant challenges for early season crop mapping, as it leads to missing or corrupted spectral information. Synthetic aperture…
Intrusion detection mechanisms for VoIP applications
Mohamed El Baker Nassar, Radu State, Olivier Festor
VoIP applications are emerging today as an important component in business and communication industry. In this paper, we address the intrusion detection and prevention in VoIP netw…
From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents
Tatiana Petrova, Boris Bliznioukov, Aleksandr Puzikov +1
The Web of Agents (WoA) transforms the document-centric Web into an environment of autonomous agents acting on users' behalf, a vision newly tractable as large language models (LLM…
The Art of The Scam: Demystifying Honeypots in Ethereum Smart Contracts
Christof Ferreira Torres, Mathis Steichen, Radu State
Modern blockchains, such as Ethereum, enable the execution of so-called smart contracts - programs that are executed across a decentralised network of nodes. As smart contracts bec…
FedRandom: Sampling Consistent and Accurate Contribution Values in Federated Learning
Arno Geimer, Beltran Fiz Pontiveros, Radu State
Federated Learning is a privacy-preserving decentralized approach for Machine Learning tasks. In industry deployments characterized by a limited number of entities possessing abund…
MQLV: Optimal Policy of Money Management in Retail Banking with Q-Learning
Jeremy Charlier, Gaston Ormazabal, Radu State +1
Reinforcement learning has become one of the best approach to train a computer game emulator capable of human level performance. In a reinforcement learning approach, an optimal va…
On the Reduction of Biases in Big Data Sets for the Detection of Irregular Power Usage
Patrick Glauner, Radu State, Petko Valtchev +1
In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably…
SynGAN: Towards Generating Synthetic Network Attacks using GANs
Jeremy Charlier, Aman Singh, Gaston Ormazabal +2
The rapid digital transformation without security considerations has resulted in the rise of global-scale cyberattacks. The first line of defense against these attacks are Network…
LongKey: Keyphrase Extraction for Long Documents
Jeovane Honorio Alves, Radu State, Cinthia Obladen de Almendra Freitas +1
In an era of information overload, manually annotating the vast and growing corpus of documents and scholarly papers is increasingly impractical. Automated keyphrase extraction add…
Small Language Models in the Real World: Insights from Industrial Text Classification
Lujun Li, Lama Sleem, Niccolo' Gentile +2
With the emergence of ChatGPT, Transformer models have significantly advanced text classification and related tasks. Decoder-only models such as Llama exhibit strong performance an…
Human in the Loop: Interactive Passive Automata Learning via Evidence-Driven State-Merging Algorithms
Christian A. Hammerschmidt, Radu State, Sicco Verwer
We present an interactive version of an evidence-driven state-merging (EDSM) algorithm for learning variants of finite state automata. Learning these automata often amounts to reco…
WallStreetFeds: Client-Specific Tokens as Investment Vehicles in Federated Learning
Arno Geimer, Beltran Fiz Pontiveros, Radu State
Federated Learning (FL) is a collaborative machine learning paradigm which allows participants to collectively train a model while training data remains private. This paradigm is e…
XRP-NDN Overlay: Improving the Communication Efficiency of Consensus-Validation based Blockchains with an NDN Overlay
Lucian Trestioreanu, Wazen M. Shbair, Flaviene Scheidt de Cristo +1
With the growing adoption of Distributed Ledger Technologies and the subsequent scaling of these networks, there is an inherent need for efficient and resilient communication used…
Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments
Yangjie Xu, Lujun Li, Lama Sleem +6
Agent skills are widely supported by major agentic frameworks and perform well with proprietary models, yet their effectiveness for small and medium-sized open source language mode…
Elysium: Context-Aware Bytecode-Level Patching to Automatically Heal Vulnerable Smart Contracts
Christof Ferreira Torres, Hugo Jonker, Radu State
Fixing bugs is easiest by patching source code. However, source code is not always available: only 0.3% of the ~49M smart contracts that are currently deployed on Ethereum have the…
Cross Domain Early Crop Mapping using CropSTGAN
Yiqun Wang, Hui Huang, Radu State
Driven by abundant satellite imagery, machine learning-based approaches have recently been promoted to generate high-resolution crop cultivation maps to support many agricultural a…
SPON: Enabling Resilient Inter-Ledgers Payments with an Intrusion-Tolerant Overlay
Lucian Trestioreanu, Cristina Nita-Rotaru, Aanchal Malhotra +1
Payment systems are a critical component of everyday life in our society. While in many situations payments are still slow, opaque, siloed, expensive or even fail, users expect the…
Infer Your Enemies and Know Yourself, Learning in Real-Time Bidding with Partially Observable Opponents
Manxing Du, Alexander I. Cowen-Rivers, Ying Wen +4
Real-time bidding, as one of the most popular mechanisms for selling online ad slots, facilitates advertisers to reach their potential customers. The goal of bidding optimization i…
Torinj : Automated Exploitation Malware Targeting Tor Users
Gerard Wagener, Alexandre Dulaunoy, Radu State
We propose in this paper a new propagation vector for malicious software by abusing the Tor network. Tor is particularly relevant, since operating a Tor exit node is easy and invol…
Limitations of Normalization in Attention Mechanism
Timur Mudarisov, Mikhail Burtsev, Tatiana Petrova +1
This paper investigates the limitations of the normalization in attention mechanisms. We begin with a theoretical framework that enables the identification of the model's selective…
Low-Complexity Algorithm for Stackelberg Prediction Games with Global Optimality
Tong Wei, Yangjie Xu, Xinlin Wang +4
Stackelberg prediction games (SPGs) model strategic data manipulation in adversarial learning via a leader--follower interaction between a learner and a self-interested data provid…
Improving Missing Data Imputation with Deep Generative Models
Ramiro D. Camino, Christian A. Hammerschmidt, Radu State
Datasets with missing values are very common on industry applications, and they can have a negative impact on machine learning models. Recent studies introduced solutions to the pr…
Impact of Biases in Big Data
Patrick Glauner, Petko Valtchev, Radu State
The underlying paradigm of big data-driven machine learning reflects the desire of deriving better conclusions from simply analyzing more data, without the necessity of looking at…
Interpreting Finite Automata for Sequential Data
Christian Albert Hammerschmidt, Sicco Verwer, Qin Lin +1
Automaton models are often seen as interpretable models. Interpretability itself is not well defined: it remains unclear what interpretability means without first explicitly specif…
On the Volatility of Shapley-Based Contribution Metrics in Federated Learning
Arno Geimer, Beltran Fiz, Radu State
Federated learning (FL) is a collaborative and privacy-preserving Machine Learning paradigm, allowing the development of robust models without the need to centralize sensitive data…
Blockchain Governance: An Overview and Prediction of Optimal Strategies using Nash Equilibrium
Nida Khan, Tabrez Ahmad, Anass Patel +1
Blockchain governance is a subject of ongoing research and an interdisciplinary view of blockchain governance is vital to aid in further research for establishing a formal governan…
Attraction, Repulsion, and Friction: Introducing DMF, a Friction-Augmented Drifting Model
Arkadii Kazanskii, Tatiana Petrova, Konstantin Bagrianskii +2
Drifting Models [Deng et al., 2026] train a one-step generator by evolving samples under a kernel-based drift field, avoiding ODE integration at inference. The original analysis le…
Do Large Language Models Grasp The Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish
Lujun Li, Yewei Song, Lama Sleem +7
Grammar refers to the system of rules that governs the structural organization and the semantic relations among linguistic units such as sentences, phrases, and words within a give…
A Flash(bot) in the Pan: Measuring Maximal Extractable Value in Private Pools
Ben Weintraub, Christof Ferreira Torres, Cristina Nita-Rotaru +1
The rise of Ethereum has lead to a flourishing decentralized marketplace that has, unfortunately, fallen victim to frontrunning and Maximal Extractable Value (MEV) activities, wher…
A Data Science Approach for Honeypot Detection in Ethereum
Ramiro Camino, Christof Ferreira Torres, Mathis Baden +1
Ethereum smart contracts have recently drawn a considerable amount of attention from the media, the financial industry and academia. With the increase in popularity, malicious user…
Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?
Yewei Song, Lujun Li, Cedric Lothritz +6
Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-res…
Is Big Data Sufficient for a Reliable Detection of Non-Technical Losses?
Patrick Glauner, Angelo Migliosi, Jorge Meira +3
Non-technical losses (NTL) occur during the distribution of electricity in power grids and include, but are not limited to, electricity theft and faulty meters. In emerging countri…
Know Your Model (KYM): Increasing Trust in AI and Machine Learning
Mary Roszel, Robert Norvill, Jean Hilger +1
The widespread utilization of AI systems has drawn attention to the potential impacts of such systems on society. Of particular concern are the consequences that prediction errors…
The Challenge of Non-Technical Loss Detection using Artificial Intelligence: A Survey
Patrick Glauner, Jorge Augusto Meira, Petko Valtchev +2
Detection of non-technical losses (NTL) which include electricity theft, faulty meters or billing errors has attracted increasing attention from researchers in electrical engineeri…
ConFuzzius: A Data Dependency-Aware Hybrid Fuzzer for Smart Contracts
Christof Ferreira Torres, Antonio Ken Iannillo, Arthur Gervais +1
Smart contracts are Turing-complete programs that are executed across a blockchain. Unlike traditional programs, once deployed, they cannot be modified. As smart contracts carry mo…
User-Device Authentication in Mobile Banking using APHEN for Paratuck2 Tensor Decomposition
Jeremy Charlier, Eric Falk, Radu State +1
The new financial European regulations such as PSD2 are changing the retail banking services. Noticeably, the monitoring of the personal expenses is now opened to other institution…
How Much Does Persuasion Strategy Matter? LLM-Annotated Evidence from Charitable Donation Dialogues
Tatiana Petrova, Stanislav Sokol, Radu State
Which persuasion strategies, if any, are associated with donation compliance? Answering this requires fine-grained strategy labels across a full corpus and statistical tests correc…
Exploring the Impact of Temperature on Large Language Models:Hot or Cold?
Lujun Li, Lama Sleem, Niccolo' Gentile +2
The sampling temperature, a critical hyperparameter in large language models (LLMs), modifies the logits before the softmax layer, thereby reshaping the distribution of output toke…
Geometric Analysis of Token Selection in Multi-Head Attention
Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova +1
We present a geometric framework for analysing multi-head attention in large language models (LLMs). Without altering the mechanism, we view standard attention through a top-N sele…
Minority Class Oversampling for Tabular Data with Deep Generative Models
Ramiro Camino, Christian Hammerschmidt, Radu State
In practice, machine learning experts are often confronted with imbalanced data. Without accounting for the imbalance, common classifiers perform poorly and standard evaluation met…
Non-Negative PARATUCK2 Tensor Decomposition Combined to LSTM Network For Smart Contracts Profiling
Jeremy Charlier, Radu State, Jean Hilger
Smart contracts are programs stored and executed on a blockchain. The Ethereum platform, an open-source blockchain-based platform, has been designed to use these programs offering…
Temporal-Spatial Tubelet Embedding for Cloud-Robust MSI Reconstruction using MSI-SAR Fusion: A Multi-Head Self-Attention Video Vision Transformer Approach
Yiqun Wang, Lujun Li, Meiru Yue +1
Cloud cover in multispectral imagery (MSI) significantly hinders early-season crop mapping by corrupting spectral information. Existing Vision Transformer(ViT)-based time-series re…
Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations
Patrick Glauner, Niklas Dahringer, Oleksandr Puhachov +4
Power grids are critical infrastructure assets that face non-technical losses (NTL) such as electricity theft or faulty meters. NTL may range up to 40% of the total electricity dis…