collaborators

12 papers

cs.CR2026

How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

Lorenzo Guerra, Thomas Chapuis, Guillaume Duc +2

Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choic…

math.ST2026

Polar Depth for Potentially Heavy-Tailed Data

Stephan Clemençon, Carlos Fernándes, Pavlo Mozharovskyi +1

Motivated by the analysis of the behaviour of extremes from multivariate heavy-tailed distributions, we introduce a novel notion of statistical depth, referred to as Polar Depth. T…

cs.LG2026

Study of Training Dynamics for Memory-Constrained Fine-Tuning

Aël Quélennec, Nour Hezbri, Pavlo Mozharovskyi +2

Memory-efficient training of deep neural networks has become increasingly important as models grow larger while deployment environments impose strict resource constraints. We propo…

cs.LG2025

Self-Supervised Learning of Graph Representations for Network Intrusion Detection

Lorenzo Guerra, Thomas Chapuis, Guillaume Duc +2

Detecting intrusions in network traffic is a challenging task, particularly under limited supervision and constantly evolving attack patterns. While recent works have leveraged gra…

cs.LG2025

Memory Constrained Dynamic Subnetwork Update for Transfer Learning

Aël Quélennec, Pavlo Mozharovskyi, Van-Tam Nguyen +1

On-device neural network training faces critical memory constraints that limit the adaptation of pre-trained models to downstream tasks. We present MeDyate, a theoretically-grounde…

stat.ML2025

Data Depth as a Risk

Arturo Castellanos, Pavlo Mozharovskyi

Data depths are score functions that quantify in an unsupervised fashion how central is a point inside a distribution, with numerous applications such as anomaly detection, multiva…