12 papers
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…
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…
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…
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…
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…
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…