1 citations · 2 across the 10 of their papers we have counts for
12 papers
Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics
Antonio Emanuele Cinà, Giovanni Scodeller, Cecilia Caterina Pasquale +5
The rapid evolution of Intelligent Transportation Systems and Logistics (ITS\&L) has become a cornerstone of the modern social economy, relying heavily on the integration of Data,…
Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness
Andrea Ponte, Luca Demetrio, Luca Oneto +2
Industrial Windows malware detectors are commonly described as Compound AI Systems composed of multiple heterogeneous components, including rule-based mechanisms as well as machine…
Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering
Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà +3
Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computa…
Mixture-of-Experts RL for Fault-Tolerant Legged Locomotion
Giulio Turrisi, Ozan Pali, Luca Oneto +1
Legged robots deployed in planetary exploration and other remote environments must maintain reliable locomotion despite actuator failures and challenging terrain conditions. Althou…
Latent-space Attacks for Refusal Evasion in Language Models
Giorgio Piras, Raffaele Mura, Fabio Brau +4
Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by…
Degradation-aware Predictive Energy Management for Fuel Cell-Battery Ship Power System with Data-driven Load Forecasting
Timon Kopka, Sara Tamburello, Luca Oneto +3
Hydrogen-based zero-emission ships are a key element in the decarbonization of the maritime sector. To strengthen these their economic competitiveness, it is key to drive their cos…
SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
Giorgio Piras, Raffaele Mura, Fabio Brau +3
Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic i…
Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection
Andrea Ponte, Luca Demetrio, Luca Oneto +3
Malware detection increasingly relies on AI systems that integrate signature-based detection with machine learning. However, these components are typically developed and combined i…
Empirical Quantification of Spurious Correlations in Malware Detection
Bianca Perasso, Ludovico Lozza, Andrea Ponte +3
End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevanc…
Training-Free Constrained Generation With Stable Diffusion Models
Stefano Zampini, Jacob K. Christopher, Luca Oneto +2
Stable diffusion models represent the state-of-the-art in data synthesis across diverse domains and hold transformative potential for applications in science and engineering, e.g.,…
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
Srishti Gupta, Zhang Chen, Luca Demetrio +9
Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is consi…
Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates
Daniele Angioni, Luca Demetrio, Maura Pintor +4
Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mis…