Author

Luca Demetrio

h-index 13 View on Semantic Scholar

We have 4 of 46 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness

A novel methodology is proposed that explicitly balances the trade-off among detection performance, computational requirements, and robustness, and introduces system-level threat models that capture how attackers exploit different degrees of knowledge to evade the entire Compound AI System rather than isolated detector...

Andrea Ponte, Luca Demetrio, Luca Oneto et al. · 0 citations

Open access May 2024

Certified Adversarial Robustness of End-to-End Malware Detectors via (De)Randomized Smoothing

A novel deterministic certification schema based on (de)randomized smoothing that guarantees that each chunk either contains or does not contain an adversarial perturbation, enabling it to handle manipulations occurring at arbitrary locations within the program and compute deterministic estimates of the perturbation ma...

Daniel Gibert, Luca Demetrio, Giulio Zizzo et al. · ACM Transactions on Privacy... · 4 citations

#machine learning Open access Mar 2025

Trust Under Siege: Label Spoofing Attacks Against Machine Learning for Android Malware Detection

Concerns are raised about the trustworthiness of ML training processes based on AV annotations and it is argued that further investigation is needed to develop more reliable labeling strategies.

Tianwei Lan, Luca Demetrio, F. Nait-Abdesselam et al. · IEEE Transactions on Informa... · 5 citations

Jul 2026

EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability

ExE-Bench assesses performance, temporal and adversarial robustness, and computational overhead, aggregating them into a single score for direct and fair model comparison, and highlights how evaluations conducted only after deployment are suboptimal and unable to provide a complete picture of their performance.

Andrea Ponte, Daniel Gibert, M. Kozák et al. · arXiv.org · 0 citations