2 citations · 3 across the 17 of their papers we have counts for
20 papers
Absorbed in Inertia: Activation Analysis for Computer-Use Agents
Giulio Segalini, Zhi Wen Soi, Jérémie Decouchant +1
Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, actions, and r…
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
Elena Dumitrescu, Gert Lek, Lydia Y. Chen +1
Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understoo…
Robust and Automated Reconfiguration of Byzantine Wide-Area Replication
Rowdy Chotkan, Bulat Nasrulin, Johan Pouwelse +1
Distributed systems handle adversarial nodes through redundancy, which imposes a significant performance overhead. In blockchain systems, Byzantine fault-tolerant state-machine rep…
Dynamic Topology Optimization for Non-IID Data in Decentralized Learning
Bart Cox, Antreas Ioannou, Jérémie Decouchant
Decentralized learning (DL) enables a set of nodes to train a model collaboratively without central coordination, offering benefits for privacy and scalability. However, DL struggl…
Balancing Fairness and Performance in Multi-User Spark Workloads with Dynamic Scheduling (extended version)
Dāvis Kažemaks, Laurens Versluis, Burcu Kulahcioglu Ozkan +1
Apache Spark is a widely adopted framework for large-scale data processing. However, in industrial analytics environments, Spark's built-in schedulers, such as FIFO and fair schedu…
NEMO: Faster Parallel Execution for Highly Contended Blockchain Workloads (Full version)
François Ezard, Can Umut Ileri, Jérémie Decouchant
Following the design of more efficient blockchain consensus algorithms, the execution layer has emerged as the new performance bottleneck of blockchains, especially under high cont…
StarveSpam: Mitigating Spam with Local Reputation in Permissionless Blockchains
Rowdy Chotkan, Bulat Nasrulin, Jérémie Decouchant +1
Spam poses a growing threat to blockchain networks. Adversaries can easily create multiple accounts to flood transaction pools, inflating fees and degrading service quality. Existi…
Go With The Flow: Churn-Tolerant Decentralized Training of Large Language Models
Nikolay Blagoev, Bart Cox, Jérémie Decouchant +1
Motivated by the emergence of large language models (LLMs) and the importance of democratizing their training, we propose GWTF, the first crash tolerant practical decentralized tra…
Taming Double-Spending in Offline Payments with Reputation-Weighted Loan Networks
Nektarios Evangelou, Rowdy Chotkan, Bulat Nasrulin +1
Blockchain solutions typically assume a synchronous network to ensure consistency and achieve consensus. In contrast, offline transaction systems aim to enable users to agree on an…
SoK: Microservice Architectures from a Dependability Perspective
Dāvis Kažemaks, Jérémie Decouchant
The microservice software architecture leverages the idea of splitting large monolithic applications into multiple smaller services that interact using lightweight communication sc…
Optimizing Streamlined Blockchain Consensus with Generalized Weighted Voting and Enhanced Leader Rotation
Diana Micloiu, Rowdy Chotkan, Jérémie Decouchant
Streamlined Byzantine Fault Tolerant (BFT) protocols, such as HotStuff [PODC'19], and weighted voting represent two possible strategies to improve consensus in the distributed syst…
Partition Detection in Byzantine Networks
Yérom-David Bromberg, Jérémie Decouchant, Manon Sourisseau +1
Detecting and handling network partitions is a fundamental requirement of distributed systems. Although existing partition detection methods in arbitrary graphs tolerate unreliable…
Reliable Communication in Hybrid Authentication and Trust Models
Rowdy Chotkan, Bart Cox, Vincent Rahli +1
Reliable communication is a fundamental distributed communication abstraction that allows any two nodes of a network to communicate with each other. It is necessary for more powerf…
Asynchronous Multi-Server Federated Learning for Geo-Distributed Clients
Yuncong Zuo, Bart Cox, Lydia Y. Chen +1
Federated learning (FL) systems enable multiple clients to train a machine learning model iteratively through synchronously exchanging the intermediate model weights with a single…
Asynchronous Byzantine Federated Learning
Bart Cox, Abele Mălan, Lydia Y. Chen +1
Federated learning (FL) enables a set of geographically distributed clients to collectively train a model through a server. Classically, the training process is synchronous, but ca…
Training Diffusion Models with Federated Learning
Matthijs de Goede, Bart Cox, Jérémie Decouchant
The training of diffusion-based models for image generation is predominantly controlled by a select few Big Tech companies, raising concerns about privacy, copyright, and data auth…
Parameterizing Federated Continual Learning for Reproducible Research
Bart Cox, Jeroen Galjaard, Aditya Shankar +2
Federated Learning (FL) systems evolve in heterogeneous and ever-evolving environments that challenge their performance. Under real deployments, the learning tasks of clients can a…
CCBNet: Confidential Collaborative Bayesian Networks Inference
Abele Mălan, Jérémie Decouchant, Thiago Guzella +1
Effective large-scale process optimization in manufacturing industries requires close cooperation between different human expert parties who encode their knowledge of related domai…
Share Secrets for Privacy: Confidential Forecasting with Vertical Federated Learning
Aditya Shankar, Jérémie Decouchant, Dimitra Gkorou +2
Vertical federated learning (VFL) is a promising area for time series forecasting in many applications, such as healthcare and manufacturing. Critical challenges to address include…
Liveness Checking of the HotStuff Protocol Family
Jérémie Decouchant, Burcu Kulahcioglu Ozkan, Yanzhuo Zhou
Byzantine consensus protocols aim at maintaining safety guarantees under any network synchrony model and at providing liveness in partially or fully synchronous networks. However,…