28 citations · 56 across the 21 of their papers we have counts for
21 papers
Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation
Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji +2
While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- er…
Toward Agentic SysAdmin: Rethinking System Administration with AI Agents
Gianmaria Frigo, Davide Saladino, Alberto Castagnaro +4
The growing complexity of computer networks, driven by cloud-native architectures, heterogeneous devices, and distributed systems, places increasing pressure on network administrat…
QUACK! Making the (Rubber) Ducky Talk: A Systematic Study of Keystroke Dynamics for HID Injection Detection
Alessandro Lotto, Francesco Marchiori, Mauro Conti
Modern computing systems implicitly trust human input devices, allowing USB Human Interface Device (HID) emulators, such as the USB Rubber Ducky, to inject arbitrary keystrokes whi…
Preventing Robotic Jailbreaking via Multimodal Domain Adaptation
Francesco Marchiori, Rohan Sinha, Christopher Agia +4
Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to jailbreaking attacks that bypass safety me…
Inference Attacks on Encrypted Online Voting via Traffic Analysis
Anastasiia Belousova, Francesco Marchiori, Mauro Conti
Online voting enables individuals to participate in elections remotely, offering greater efficiency and accessibility in both governmental and organizational settings. As this meth…
DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?
Francesco Marchiori, Marco Alecci, Luca Pajola +1
Adversarial examples are small and often imperceptible perturbations crafted to fool machine learning models. These attacks seriously threaten the reliability of deep neural networ…
Profiling Electric Vehicles via Early Charging Voltage Patterns
Francesco Marchiori, Denis Donadel, Alessandro Brighente +1
Electric Vehicles (EVs) are rapidly gaining adoption as a sustainable alternative to fuel-powered vehicles, making secure charging infrastructure essential. Despite traditional aut…
PQ-CAN: A Framework for Simulating Post-Quantum Cryptography in Embedded Systems
Mauro Conti, Francesco Marchiori, Sebastiano Matarazzo +1
The rapid development of quantum computers threatens traditional cryptographic schemes, prompting the need for Post-Quantum Cryptography (PQC). Although the NIST standardization pr…
Can LLMs Classify CVEs? Investigating LLMs Capabilities in Computing CVSS Vectors
Francesco Marchiori, Denis Donadel, Mauro Conti
Common Vulnerability and Exposure (CVE) records are fundamental to cybersecurity, offering unique identifiers for publicly known software and system vulnerabilities. Each CVE is ty…
Leaky Batteries: A Novel Set of Side-Channel Attacks on Electric Vehicles
Francesco Marchiori, Mauro Conti
Advancements in battery technology have accelerated the adoption of Electric Vehicles (EVs) due to their environmental benefits. However, their growing sophistication introduces se…
Moshi Moshi? A Model Selection Hijacking Adversarial Attack
Riccardo Petrucci, Luca Pajola, Francesco Marchiori +2
Model selection is a fundamental task in Machine Learning~(ML), focusing on selecting the most suitable model from a pool of candidates by evaluating their performance on specific…
RedactBuster: Entity Type Recognition from Redacted Documents
Mirco Beltrame, Mauro Conti, Pierpaolo Guglielmin +2
The widespread exchange of digital documents in various domains has resulted in abundant private information being shared. This proliferation necessitates redaction techniques to p…
CANEDERLI: On The Impact of Adversarial Training and Transferability on CAN Intrusion Detection Systems
Francesco Marchiori, Mauro Conti
The growing integration of vehicles with external networks has led to a surge in attacks targeting their Controller Area Network (CAN) internal bus. As a countermeasure, various In…
Can LLMs Understand Computer Networks? Towards a Virtual System Administrator
Denis Donadel, Francesco Marchiori, Luca Pajola +1
Recent advancements in Artificial Intelligence, and particularly Large Language Models (LLMs), offer promising prospects for aiding system administrators in managing the complexity…
FaultGuard: A Generative Approach to Resilient Fault Prediction in Smart Electrical Grids
Emad Efatinasab, Francesco Marchiori, Alessandro Brighente +2
Predicting and classifying faults in electricity networks is crucial for uninterrupted provision and keeping maintenance costs at a minimum. Thanks to the advancements in the field…
A Survey and Comparative Analysis of Security Properties of CAN Authentication Protocols
Alessandro Lotto, Francesco Marchiori, Alessandro Brighente +1
The large number of Electronic Control Units (ECUs) mounted on modern cars and their expansive communication capabilities create a substantial attack surface for potential exploita…
AGIR: Automating Cyber Threat Intelligence Reporting with Natural Language Generation
Filippo Perrina, Francesco Marchiori, Mauro Conti +1
Cyber Threat Intelligence (CTI) reporting is pivotal in contemporary risk management strategies. As the volume of CTI reports continues to surge, the demand for automated tools to…
Your Battery Is a Blast! Safeguarding Against Counterfeit Batteries with Authentication
Francesco Marchiori, Mauro Conti
Lithium-ion (Li-ion) batteries are the primary power source in various applications due to their high energy and power density. Their market was estimated to be up to 48 billion U.…
Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability
Marco Alecci, Mauro Conti, Francesco Marchiori +2
Evasion attacks are a threat to machine learning models, where adversaries attempt to affect classifiers by injecting malicious samples. An alarming side-effect of evasion attacks…
When Authentication Is Not Enough: Breaking Behavior-Based Driver Authentication Systems
Emad Efatinasab, Francesco Marchiori, Denis Donadel +2
Researchers extensively explored behavior-based driver authentication systems in vehicles. Pushed by advances in Artificial Intelligence (AI), these systems employ powerful models…
STIXnet: A Novel and Modular Solution for Extracting All STIX Objects in CTI Reports
Francesco Marchiori, Mauro Conti, Nino Vincenzo Verde
The automatic extraction of information from Cyber Threat Intelligence (CTI) reports is crucial in risk management. The increased frequency of the publications of these reports has…