129 citations · 229 across the 21 of their papers we have counts for
22 papers
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…
From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists
Stefano Cecconello, Mauro Conti, Luca Pajola +2
The pervasive integration of AI has enabled Offensive AI: the exploitation of AI for malicious ends across the cyber-kill chain. A critical manifestation is the user attribute infe…
E-PhishGen: Unlocking Novel Research in Phishing Email Detection
Luca Pajola, Eugenio Caripoti, Stefan Banzer +3
Every day, our inboxes are flooded with unsolicited emails, ranging between annoying spam to more subtle phishing scams. Unfortunately, despite abundant prior efforts proposing sol…
FD4QC: Application of Classical and Quantum-Hybrid Machine Learning for Financial Fraud Detection A Technical Report
Matteo Cardaioli, Luca Marangoni, Giada Martini +5
The increasing complexity and volume of financial transactions pose significant challenges to traditional fraud detection systems. This technical report investigates and compares t…
The Hidden Threat in Plain Text: Attacking RAG Data Loaders
Alberto Castagnaro, Umberto Salviati, Mauro Conti +2
Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhan…
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…
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…
Elephant in the Room: Dissecting and Reflecting on the Evolution of Online Social Network Research
Luca Pajola, Saskia Laura Schröer, Pier Paolo Tricomi +2
Billions of individuals engage with Online Social Networks (OSN) daily. The owners of OSN try to meet the demands of their end-users while complying with business necessities. Such…
Offensive AI: Enhancing Directory Brute-forcing Attack with the Use of Language Models
Alberto Castagnaro, Mauro Conti, Luca Pajola
Web Vulnerability Assessment and Penetration Testing (Web VAPT) is a comprehensive cybersecurity process that uncovers a range of vulnerabilities which, if exploited, could comprom…
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…
"All of Me": Mining Users' Attributes from their Public Spotify Playlists
Pier Paolo Tricomi, Luca Pajola, Luca Pasa +1
In the age of digital music streaming, playlists on platforms like Spotify have become an integral part of individuals' musical experiences. People create and publicly share their…
Invisible Threats: Backdoor Attack in OCR Systems
Mauro Conti, Nicola Farronato, Stefanos Koffas +2
Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents. Today, the state-of-the-art is achieved by exploiting deep neural networks. Howeve…
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…
Boosting Big Brother: Attacking Search Engines with Encodings
Nicholas Boucher, Luca Pajola, Ilia Shumailov +2
Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation. By imperceptibly perturbing text using uncommon encoded representations, adv…
Social Honeypot for Humans: Luring People through Self-managed Instagram Pages
Sara Bardi, Mauro Conti, Luca Pajola +1
Social Honeypots are tools deployed in Online Social Networks (OSN) to attract malevolent activities performed by spammers and bots. To this end, their content is designed to be of…
Going In Style: Audio Backdoors Through Stylistic Transformations
Stefanos Koffas, Luca Pajola, Stjepan Picek +1
This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects. We first formalize stylistic tr…
You Can't Hide Behind Your Headset: User Profiling in Augmented and Virtual Reality
Pier Paolo Tricomi, Federica Nenna, Luca Pajola +2
Virtual and Augmented Reality (VR, AR) are increasingly gaining traction thanks to their technical advancement and the need for remote connections, recently accentuated by the pand…
SoK: Explainable Machine Learning for Computer Security Applications
Azqa Nadeem, Daniël Vos, Clinton Cao +4
Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of…
The Cross-evaluation of Machine Learning-based Network Intrusion Detection Systems
Giovanni Apruzzese, Luca Pajola, Mauro Conti
Enhancing Network Intrusion Detection Systems (NIDS) with supervised Machine Learning (ML) is tough. ML-NIDS must be trained and evaluated, operations requiring data where benign a…
Captcha Attack: Turning Captchas Against Humanity
Mauro Conti, Luca Pajola, Pier Paolo Tricomi
Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thous…
Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack
Luca Pajola, Mauro Conti
The increased demand for machine learning applications made companies offer Machine-Learning-as-a-Service (MLaaS). In MLaaS (a market estimated 8000M USD by 2025), users pay for we…
All You Need is "Love": Evading Hate-speech Detection
Tommi Gröndahl, Luca Pajola, Mika Juuti +2
With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem. In this paper, we reproduce seven sta…