Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from VLDB 2026 / reviewers in the wild / expert

Vittorio Miori

dblp:38/791 · DBLP profile ↗
← Back
2ranked-venue papers
0as first author
1since 2021 · last 2025
0000-0003-3536-283XORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Security and privacy · 1 · 1 since 2021Human-computer interaction and ubiquitous computing · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Network and information security
1 paper
Security and privacy of machine learning · 100%
Artificial intelligence
1 paper
Efficient and distributed learning · 100%
Databases, data mining, and information retrieval
1 paper
Data mining · 100%

Topics — the 7 heaviest of 7, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Efficient and distributed learning
federated learning		 0.912025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025
Machine learning › Efficient and distributed learning › federated learning › model aggregation
robust aggregation		 0.912025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025
Security and privacy of machine learning
federated learning security		 0.912025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025
Security and privacy of machine learning › federated learning security
malicious client detection		 0.912025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025
Security and privacy of machine learning › poisoning attack
model poisoning attack		 0.912025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025
Data mining
anomaly detection		 0.312025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025
Data mining › anomaly detection
time series anomaly detection		 0.312025
Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates · IEEE Trans. Inf. Forensics Secur. 2025

Methods — techniques the papers use, named apart from their topics

outlier detection · 2.6matrix autoregressive forecasting · 2.6
YearPublicationVenuePosition
2025 Securing Federated Learning Against Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection on Local Updates
abstract
Current defense mechanisms against model poisoning attacks in federated learning (FL) systems have proven effective up to a certain threshold of malicious clients (e.g., 25% to 50%). In this work, we introduce FLANDERS, a novel pre-aggregation filter for FL that is resilient to large-scale model poisoning attacks, i.e., when malicious clients far exceed legitimate participants. FLANDERS treats the sequence of local models sent by clients in each FL round as a matrix-valued time series. Then, it identifies malicious client updates as outliers in this time series by comparing actual observations with estimates generated by a matrix autoregressive forecasting model maintained by the server. Experiments conducted in several non-iid FL setups show that FLANDERS significantly improves robustness across a wide spectrum of attacks when paired with standard and robust aggregation methods.
Edoardo Gabrielli, Dimitri Belli, Zoe Matrullo, Vittorio Miori, Gabriele Tolomei
 IEEE Trans. Inf. Forensics Secur.4
2002 Remote Control of Home Automation Systems with Mobile Devices
Luca Tarrini, Rolando Bianchi Bandinelli, Vittorio Miori, Graziano Bertini
 Mobile HCI3